diff --git "a/146m174b400m/3425869.out" "b/146m174b400m/3425869.out" new file mode 100644--- /dev/null +++ "b/146m174b400m/3425869.out" @@ -0,0 +1,5664 @@ +Model parameters: d_model 768 ffw_size 3072 kv_size 64 n_heads 12 n_layers 15 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 15 --hidden-size 768 --num-attention-heads 12 --kv-channels 64 --ffn-hidden-size 3072 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 256 --train-samples 1 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-146m174b400mval --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 1 --lr-warmup-samples 0 --clip-grad 1.0 --weight-decay 1e-1 --no-load-optim --reset-progress --override-lr-scheduler --log-interval 10 --save-interval 1000 --eval-interval 1 --eval-iters 100 --eval-only true --tensorboard-dir tensorboard_146m174b400mval --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_146m174b400m --load checkpoints_146m174b400m --train-weighted-split-paths-path train14b.txt --valid-weighted-split-paths-path val.txt --data-impl mmap --deepspeed --deepspeed_config ds_configs/3425869.json --zero-stage 0 +START 3425869: Fri 28 Apr 2023 12:07:08 AM EEST +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 46.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 40.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 39.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +4: +4: +4: ======================= ROCm System Management Interface ======================= +4: ================================= Concise Info ================================= +4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +4: 0 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 2 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 4 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: 6 38.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +4: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +4: ================================================================================ +4: ============================= End of ROCm SMI Log ============================== +7: +7: +7: ======================= ROCm System Management Interface ======================= +7: ================================= Concise Info ================================= +7: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +7: 0 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 2 40.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 4 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: 6 36.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +7: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +7: ================================================================================ +7: ============================= End of ROCm SMI Log ============================== +5: +5: +5: ======================= ROCm System Management Interface ======================= +5: ================================= Concise Info ================================= +5: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +5: 0 45.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 2 48.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 4 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: 6 39.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +5: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +5: ================================================================================ +5: ============================= End of ROCm SMI Log ============================== +3: +3: +3: ======================= ROCm System Management Interface ======================= +3: ================================= Concise Info ================================= +3: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +3: 0 49.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 2 47.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 4 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: 6 41.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +3: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +3: ================================================================================ +3: ============================= End of ROCm SMI Log ============================== +6: +6: +6: ======================= ROCm System Management Interface ======================= +6: ================================= Concise Info ================================= +6: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +6: 0 48.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 2 37.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 4 46.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: 6 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +6: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +6: ================================================================================ +6: ============================= End of ROCm SMI Log ============================== +2: +2: +2: ======================= ROCm System Management Interface ======================= +2: ================================= Concise Info ================================= +2: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +2: 0 47.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 2 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 4 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: 6 45.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +2: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +2: ================================================================================ +2: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 43.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 39.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +0: Launching on nid007028 (0/8), master nid007028 port 9999, GPUs 8, CUDA: True +6: Launching on nid007034 (6/8), master nid007028 port 9999, GPUs 8, CUDA: True +5: Launching on nid007033 (5/8), master nid007028 port 9999, GPUs 8, CUDA: True +3: Launching on nid007031 (3/8), master nid007028 port 9999, GPUs 8, CUDA: True +7: Launching on nid007035 (7/8), master nid007028 port 9999, GPUs 8, CUDA: True +2: Launching on nid007030 (2/8), master nid007028 port 9999, GPUs 8, CUDA: True +4: Launching on nid007032 (4/8), master nid007028 port 9999, GPUs 8, CUDA: True +1: Launching on nid007029 (1/8), master nid007028 port 9999, GPUs 8, CUDA: True +0: using world size: 64, data-parallel-size: 64, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... False +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 64 +0: data_path ....................................... None +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/3425869.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1 +0: eval_iters ...................................... 100 +0: eval_only ....................................... True +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 3072 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 256 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 768 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-146m174b400mval +0: kv_channels ..................................... 64 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_146m174b400m +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... None +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 1 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 0 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... True +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 12 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 15 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... True +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: reset_progress .................................. True +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_146m174b400m +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... None +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_146m174b400mval +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 1 +0: train_tokens .................................... None +0: train_weighted_split_names ...................... ['train'] +0: train_weighted_split_paths ...................... [['/scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_14B_text_document']] +0: train_weighted_split_paths_path ................. None +0: train_weighted_split_splits ..................... [['0:1']] +0: train_weighted_split_weights .................... [['1.0']] +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... ['validation'] +0: valid_weighted_split_paths ...................... [['/scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document']] +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... [['0:1']] +0: valid_weighted_split_weights .................... [['1.0']] +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 64 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +7: > setting tensorboard ... +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2023-04-28 00:09:01,549] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.089 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: [1/1] c++ scaled_upper_triang_masked_softmax_hip.cuda.o scaled_upper_triang_masked_softmax_hip.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/opt/rocm/lib -lamdhip64 -o scaled_upper_triang_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: [1/1] c++ scaled_masked_softmax_hip.cuda.o scaled_masked_softmax_hip.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/opt/rocm/lib -lamdhip64 -o scaled_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: [1/1] c++ layer_norm_hip_kernel.cuda.o layer_norm_cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/opt/rocm/lib -lamdhip64 -o fused_mix_prec_layer_norm_cuda.so +0: >>> done with compiling and loading fused kernels. Compilation time: 24.609 seconds +0: time to initialize megatron (seconds): 9.276 +0: [after megatron is initialized] datetime: 2023-04-28 00:09:29 +0: building GPT model ... +0: [2023-04-28 00:09:29,415] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2023-04-28 00:09:29,415] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2023-04-28 00:09:29,415] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.3 GB, percent = 8.0% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15, ProcessCoord(pipe=0, data=16, model=0): 16, ProcessCoord(pipe=0, data=17, model=0): 17, ProcessCoord(pipe=0, data=18, model=0): 18, ProcessCoord(pipe=0, data=19, model=0): 19, ProcessCoord(pipe=0, data=20, model=0): 20, ProcessCoord(pipe=0, data=21, model=0): 21, ProcessCoord(pipe=0, data=22, model=0): 22, ProcessCoord(pi +0: pe=0, data=23, model=0): 23, ProcessCoord(pipe=0, data=24, model=0): 24, ProcessCoord(pipe=0, data=25, model=0): 25, ProcessCoord(pipe=0, data=26, model=0): 26, ProcessCoord(pipe=0, data=27, model=0): 27, ProcessCoord(pipe=0, data=28, model=0): 28, ProcessCoord(pipe=0, data=29, model=0): 29, ProcessCoord(pipe=0, data=30, model=0): 30, ProcessCoord(pipe=0, data=31, model=0): 31, ProcessCoord(pipe=0, data=32, model=0): 32, ProcessCoord(pipe=0, data=33, model=0): 33, ProcessCoord(pipe=0, data=34, model=0): 34, ProcessCoord(pipe=0, data=35, model=0): 35, ProcessCoord(pipe=0, data=36, model=0): 36, ProcessCoord(pipe=0, data=37, model=0): 37, ProcessCoord(pipe=0, data=38, model=0): 38, ProcessCoord(pipe=0, data=39, model=0): 39, ProcessCoord(pipe=0, data=40, model=0): 40, ProcessCoord(pipe=0, data=41, model=0): 41, ProcessCoord(pipe=0, data=42, model=0): 42, ProcessCoord(pipe=0, data=43, model=0): 43, ProcessCoord(pipe=0, data=44, model=0): 44, ProcessCoord(pipe=0, data=45, model=0): 45, ProcessCoord(pipe=0, data=4 +0: 6, model=0): 46, ProcessCoord(pipe=0, data=47, model=0): 47, ProcessCoord(pipe=0, data=48, model=0): 48, ProcessCoord(pipe=0, data=49, model=0): 49, ProcessCoord(pipe=0, data=50, model=0): 50, ProcessCoord(pipe=0, data=51, model=0): 51, ProcessCoord(pipe=0, data=52, model=0): 52, ProcessCoord(pipe=0, data=53, model=0): 53, ProcessCoord(pipe=0, data=54, model=0): 54, ProcessCoord(pipe=0, data=55, model=0): 55, ProcessCoord(pipe=0, data=56, model=0): 56, ProcessCoord(pipe=0, data=57, model=0): 57, ProcessCoord(pipe=0, data=58, model=0): 58, ProcessCoord(pipe=0, data=59, model=0): 59, ProcessCoord(pipe=0, data=60, model=0): 60, ProcessCoord(pipe=0, data=61, model=0): 61, ProcessCoord(pipe=0, data=62, model=0): 62, ProcessCoord(pipe=0, data=63, model=0): 63} +0: [2023-04-28 00:09:31,406] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=22 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: ParallelTransformerLayerPipe +0: 7: ParallelTransformerLayerPipe +0: 8: ParallelTransformerLayerPipe +0: 9: ParallelTransformerLayerPipe +0: 10: ParallelTransformerLayerPipe +0: 11: ParallelTransformerLayerPipe +0: 12: ParallelTransformerLayerPipe +0: 13: ParallelTransformerLayerPipe +0: 14: ParallelTransformerLayerPipe +0: 15: ParallelTransformerLayerPipe +0: 16: ParallelTransformerLayerPipe +0: 17: ParallelTransformerLayerPipe +0: 18: undo +0: 19: MixedFusedLayerNorm +0: 20: EmbeddingPipe +0: 21: float16_to_fp32 +0: loss: CrossEntropy +0: [2023-04-28 00:09:31,638] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2023-04-28 00:09:31,639] [INFO] [utils.py:828:see_memory_usage] MA 0.28 GB Max_MA 0.28 GB CA 0.29 GB Max_CA 0 GB +0: [2023-04-28 00:09:31,639] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.31 GB, percent = 8.0% +0: setting training iterations to 0 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2023-04-28 00:09:31,642] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2023-04-28 00:09:44,801] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2023-04-28 00:09:44,802] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2023-04-28 00:09:44,802] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2023-04-28 00:09:44,806] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2023-04-28 00:09:44,806] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2023-04-28 00:09:44,926] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2023-04-28 00:09:44,927] [INFO] [utils.py:828:see_memory_usage] MA 0.28 GB Max_MA 0.29 GB CA 0.31 GB Max_CA 0 GB +0: [2023-04-28 00:09:44,927] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.87 GB, percent = 8.3% +5: ninja: no work to do. +0: Time to load utils op: 0.3586091995239258 secondsTime to load utils op: 0.35849738121032715 seconds +0: +0: Time to load utils op: 0.3583219051361084 seconds +0: Time to load utils op: 0.35873937606811523 seconds +0: Time to load utils op: 0.35849547386169434 seconds +0: Time to load utils op: 0.35853147506713867 seconds +0: Time to load utils op: 0.35866808891296387 seconds +5: Time to load utils op: 0.3853485584259033 secondsTime to load utils op: 0.38637709617614746 seconds +5: +5: Time to load utils op: 0.385418176651001 seconds +5: Time to load utils op: 0.3863363265991211 secondsTime to load utils op: 0.3857874870300293 seconds +5: +5: Time to load utils op: 0.3864595890045166 seconds +5: Time to load utils op: 0.38666248321533203 seconds +5: Time to load utils op: 0.38587164878845215 seconds +0: Time to load utils op: 0.30973005294799805 seconds +6: Time to load utils op: 0.3413047790527344 seconds +6: Time to load utils op: 0.3413417339324951 seconds +6: Time to load utils op: 0.3939938545227051 seconds +6: Time to load utils op: 0.3413538932800293 seconds +6: Time to load utils op: 0.3413970470428467 seconds +6: Time to load utils op: 0.3411705493927002 seconds +6: Time to load utils op: 0.38790464401245117 secondsTime to load utils op: 0.3537914752960205 seconds +6: +1: Time to load utils op: 0.41773152351379395 secondsTime to load utils op: 0.4177267551422119 seconds +1: +1: Time to load utils op: 0.41773128509521484 seconds +1: Time to load utils op: 0.4177367687225342 seconds +1: Time to load utils op: 0.4173848628997803 seconds +1: Time to load utils op: 0.417752742767334 seconds +1: Time to load utils op: 0.4178035259246826 secondsTime to load utils op: 0.41780519485473633 seconds +1: +7: Time to load utils op: 0.4770200252532959 secondsTime to load utils op: 0.47860050201416016 secondsTime to load utils op: 0.4778008460998535 seconds +7: +7: +7: Time to load utils op: 0.4782412052154541 seconds +7: Time to load utils op: 0.47774410247802734 seconds +7: Time to load utils op: 0.4775698184967041 seconds +7: Time to load utils op: 0.47829246520996094 secondsTime to load utils op: 0.47893285751342773 seconds +7: +0: [2023-04-28 00:09:45,347] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2023-04-28 00:09:45,348] [INFO] [utils.py:828:see_memory_usage] MA 0.28 GB Max_MA 0.28 GB CA 0.31 GB Max_CA 0 GB +0: [2023-04-28 00:09:45,348] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.93 GB, percent = 8.1% +2: Time to load utils op: 0.5510706901550293 seconds +2: Time to load utils op: 0.5516781806945801 seconds +2: Time to load utils op: 0.55255126953125 seconds +2: Time to load utils op: 0.5521845817565918 seconds +2: Time to load utils op: 0.5520703792572021 secondsTime to load utils op: 0.5512385368347168 seconds +2: +2: Time to load utils op: 0.5514743328094482 secondsTime to load utils op: 0.5524318218231201 seconds +2: +4: Time to load utils op: 0.5494339466094971 seconds +4: Time to load utils op: 0.550482988357544 seconds +4: Time to load utils op: 0.5493724346160889 seconds +4: Time to load utils op: 0.5494379997253418 seconds +4: Time to load utils op: 0.5494048595428467 seconds +4: Time to load utils op: 0.549858808517456 seconds +4: Time to load utils op: 0.5500249862670898 secondsTime to load utils op: 0.550072431564331 seconds +4: +3: Time to load utils op: 0.5649218559265137 seconds +3: Time to load utils op: 0.5645792484283447 seconds +3: Time to load utils op: 0.5646543502807617 seconds +3: Time to load utils op: 0.5655844211578369 seconds +3: Time to load utils op: 0.5652997493743896 seconds +3: Time to load utils op: 0.5655090808868408 seconds +3: Time to load utils op: 0.5647554397583008 seconds +3: Time to load utils op: 0.5655014514923096 seconds +3: Time to load utils op: 0.0008244514465332031 seconds +3: Time to load utils op: 0.0014278888702392578 seconds +3: Time to load utils op: 0.0013630390167236328 seconds +3: Time to load utils op: 0.0013456344604492188 seconds +3: Time to load utils op: 0.0013499259948730469 seconds +3: Time to load utils op: 0.0013020038604736328 seconds +3: Time to load utils op: 0.001367807388305664 seconds +3: Time to load utils op: 0.0014226436614990234 seconds +0: Time to load utils op: 0.00047707557678222656 secondsTime to load utils op: 0.0005106925964355469 seconds +0: +0: Time to load utils op: 0.0005872249603271484 seconds +0: Time to load utils op: 0.000492095947265625 seconds +0: Time to load utils op: 0.0004940032958984375 seconds +0: Time to load utils op: 0.0004534721374511719 seconds +0: Time to load utils op: 0.0004754066467285156 seconds +5: Time to load utils op: 0.003640890121459961 seconds +5: Time to load utils op: 0.004135847091674805 seconds +5: Time to load utils op: 0.004158973693847656 seconds +5: Time to load utils op: 0.0043125152587890625 seconds +5: Time to load utils op: 0.004101276397705078 seconds +5: Time to load utils op: 0.004125833511352539 secondsTime to load utils op: 0.0039119720458984375 seconds +5: Time to load utils op: 0.004186153411865234 seconds +5: +0: [2023-04-28 00:09:45,802] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +0: [2023-04-28 00:09:45,802] [INFO] [utils.py:828:see_memory_usage] MA 0.62 GB Max_MA 0.62 GB CA 0.82 GB Max_CA 1 GB +0: [2023-04-28 00:09:45,802] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.08 GB, percent = 8.2% +0: [2023-04-28 00:09:45,906] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2023-04-28 00:09:45,906] [INFO] [utils.py:828:see_memory_usage] MA 0.62 GB Max_MA 0.62 GB CA 0.82 GB Max_CA 1 GB +0: [2023-04-28 00:09:45,906] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.08 GB, percent = 8.2% +7: Time to load utils op: 0.009854555130004883 seconds +7: Time to load utils op: 0.01910400390625 seconds +7: Time to load utils op: 0.019475460052490234 seconds +7: Time to load utils op: 0.019440889358520508 seconds +7: Time to load utils op: 0.019573688507080078 seconds +7: Time to load utils op: 0.019565820693969727 seconds +7: Time to load utils op: 0.01961374282836914 seconds +7: Time to load utils op: 0.01949310302734375 seconds +0: [2023-04-28 00:09:46,007] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2023-04-28 00:09:46,008] [INFO] [utils.py:828:see_memory_usage] MA 0.83 GB Max_MA 0.83 GB CA 1.13 GB Max_CA 1 GB +0: [2023-04-28 00:09:46,008] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.08 GB, percent = 8.2% +0: [2023-04-28 00:09:46,106] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2023-04-28 00:09:46,107] [INFO] [utils.py:828:see_memory_usage] MA 0.83 GB Max_MA 0.83 GB CA 1.13 GB Max_CA 1 GB +0: [2023-04-28 00:09:46,107] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.08 GB, percent = 8.2% +6: Time to load utils op: 0.0004661083221435547 seconds +6: Time to load utils op: 0.0005230903625488281 seconds +6: Time to load utils op: 0.0005185604095458984 seconds +6: Time to load utils op: 0.0005474090576171875 secondsTime to load utils op: 0.0005552768707275391 secondsTime to load utils op: 0.0005283355712890625 seconds +6: +6: +6: Time to load utils op: 0.0006232261657714844 secondsTime to load utils op: 0.0006163120269775391 seconds +6: +2: Time to load utils op: 0.0464940071105957 seconds +2: Time to load utils op: 0.05258011817932129 secondsTime to load utils op: 0.05254387855529785 seconds +2: +2: Time to load utils op: 0.05256772041320801 seconds +2: Time to load utils op: 0.05259108543395996 seconds +2: Time to load utils op: 0.05304312705993652 secondsTime to load utils op: 0.05304884910583496 seconds +2: +2: Time to load utils op: 0.05309557914733887 seconds +0: [2023-04-28 00:09:46,208] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: [2023-04-28 00:09:46,209] [INFO] [utils.py:828:see_memory_usage] MA 0.83 GB Max_MA 0.83 GB CA 1.13 GB Max_CA 1 GB +0: [2023-04-28 00:09:46,209] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.08 GB, percent = 8.2% +0: [2023-04-28 00:09:46,307] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2023-04-28 00:09:46,307] [INFO] [utils.py:828:see_memory_usage] MA 0.83 GB Max_MA 0.83 GB CA 1.13 GB Max_CA 1 GB +0: [2023-04-28 00:09:46,307] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.08 GB, percent = 8.2% +1: Time to load utils op: 0.0009832382202148438 secondsTime to load utils op: 0.0009980201721191406 seconds +1: +1: Time to load utils op: 0.0009913444519042969 seconds +1: Time to load utils op: 0.0012865066528320312 seconds +1: Time to load utils op: 0.0011737346649169922 seconds +1: Time to load utils op: 0.0012094974517822266 seconds +1: Time to load utils op: 0.0012614727020263672 seconds +1: Time to load utils op: 0.0013031959533691406 seconds +0: [2023-04-28 00:09:46,412] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2023-04-28 00:09:46,413] [INFO] [utils.py:828:see_memory_usage] MA 0.85 GB Max_MA 0.85 GB CA 1.13 GB Max_CA 1 GB +0: [2023-04-28 00:09:46,413] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.08 GB, percent = 8.2% +4: Time to load utils op: 0.04269242286682129 seconds +4: Time to load utils op: 0.048493146896362305 seconds +4: Time to load utils op: 0.04844975471496582 seconds +4: Time to load utils op: 0.04860997200012207 seconds +4: Time to load utils op: 0.04861330986022949 seconds +4: Time to load utils op: 0.0484766960144043 seconds +4: Time to load utils op: 0.04924654960632324 seconds +4: Time to load utils op: 0.0492100715637207 seconds +0: [2023-04-28 00:09:46,514] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2023-04-28 00:09:46,514] [INFO] [utils.py:828:see_memory_usage] MA 0.85 GB Max_MA 0.85 GB CA 1.13 GB Max_CA 1 GB +0: [2023-04-28 00:09:46,514] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.08 GB, percent = 8.2% +0: [2023-04-28 00:09:46,515] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2023-04-28 00:09:46,515] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2023-04-28 00:09:46,515] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2023-04-28 00:09:46,515] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0002, 0.0002, 0.0002], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2023-04-28 00:09:46,515] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] amp_params ................... False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] comms_config ................. +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] dump_state ................... False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2023-04-28 00:09:46,516] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] monitor_config ............... +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] pld_params ................... False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] train_batch_size ............. 256 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] world_size ................... 64 +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2023-04-28 00:09:46,517] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2023-04-28 00:09:46,518] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 256, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.0004343986511230469 seconds +0: [2023-04-28 00:09:46,518] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2023-04-28 00:09:46,530] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=22 [0, 22) STAGE_PARAMS=146525952 (146.526M) TOTAL_PARAMS=146525952 (146.526M) UNIQUE_PARAMS=146525952 (146.526M) +6: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,558] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,559] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,616] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,615] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +2: [2023-04-28 00:09:46,617] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +3: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +6: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +5: [2023-04-28 00:09:46,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +0: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +4: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +3: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt... +7: [2023-04-28 00:09:46,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/mp_rank_00_model_states.pt. +7: [2023-04-28 00:09:46,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +2: [2023-04-28 00:09:46,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +5: [2023-04-28 00:09:46,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +4: [2023-04-28 00:09:46,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +2: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +3: [2023-04-28 00:09:46,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +6: [2023-04-28 00:09:46,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +1: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +4: [2023-04-28 00:09:46,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +1: [2023-04-28 00:09:46,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +5: [2023-04-28 00:09:46,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +6: [2023-04-28 00:09:46,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +0: [2023-04-28 00:09:46,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +3: [2023-04-28 00:09:46,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +7: [2023-04-28 00:09:46,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt... +0: [2023-04-28 00:09:46,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_01-model_00-model_states.pt. +7: [2023-04-28 00:09:46,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +1: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +5: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +3: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +6: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +2: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +0: [2023-04-28 00:09:46,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +4: [2023-04-28 00:09:46,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +2: [2023-04-28 00:09:46,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +6: [2023-04-28 00:09:46,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +3: [2023-04-28 00:09:46,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:46,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:46,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:46,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +0: [2023-04-28 00:09:46,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +4: [2023-04-28 00:09:46,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +1: [2023-04-28 00:09:46,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:46,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:46,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +5: [2023-04-28 00:09:46,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:46,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:46,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:46,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:46,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:46,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:46,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:46,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:46,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:46,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:46,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:46,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:46,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:46,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:46,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:46,967] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:46,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:46,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:46,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:46,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:46,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:46,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:46,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:46,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:46,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:46,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:46,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:46,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:46,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:46,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:46,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:46,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:46,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt... +7: [2023-04-28 00:09:46,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:46,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,000] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_03-model_00-model_states.pt. +7: [2023-04-28 00:09:47,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,007] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +1: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +5: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +2: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +3: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:47,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +6: [2023-04-28 00:09:47,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +4: [2023-04-28 00:09:47,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +2: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +5: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +3: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +6: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +4: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +1: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,052] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +0: [2023-04-28 00:09:47,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,053] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,070] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt... +7: [2023-04-28 00:09:47,074] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,075] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,076] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_04-model_00-model_states.pt. +7: [2023-04-28 00:09:47,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +2: [2023-04-28 00:09:47,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +2: [2023-04-28 00:09:47,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +1: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +3: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +6: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +4: [2023-04-28 00:09:47,172] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +5: [2023-04-28 00:09:47,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,174] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,175] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,176] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,177] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,177] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +5: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +3: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +1: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +4: [2023-04-28 00:09:47,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +6: [2023-04-28 00:09:47,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +0: [2023-04-28 00:09:47,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,186] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt... +7: [2023-04-28 00:09:47,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_05-model_00-model_states.pt. +7: [2023-04-28 00:09:47,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,267] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,267] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,268] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,268] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,274] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,275] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,275] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +1: [2023-04-28 00:09:47,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,276] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,277] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +1: [2023-04-28 00:09:47,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,278] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,279] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +2: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +0: [2023-04-28 00:09:47,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +4: [2023-04-28 00:09:47,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,284] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,285] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,288] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,288] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +2: [2023-04-28 00:09:47,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,289] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +3: [2023-04-28 00:09:47,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,289] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +6: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,290] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,291] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,291] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +0: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +4: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +3: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,292] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,293] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +6: [2023-04-28 00:09:47,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,295] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,296] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,294] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt... +7: [2023-04-28 00:09:47,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,298] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,299] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,301] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,302] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,302] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,306] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,307] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +7: [2023-04-28 00:09:47,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_06-model_00-model_states.pt. +5: [2023-04-28 00:09:47,285] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,286] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +4: [2023-04-28 00:09:47,370] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,371] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,371] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +6: [2023-04-28 00:09:47,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,374] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,375] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,376] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,377] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +6: [2023-04-28 00:09:47,377] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +2: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +5: [2023-04-28 00:09:47,378] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,379] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,379] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +1: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +1: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,380] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +2: [2023-04-28 00:09:47,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,381] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,382] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +3: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +0: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,383] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,384] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,384] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,385] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +4: [2023-04-28 00:09:47,386] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,387] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,387] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +5: [2023-04-28 00:09:47,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,388] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,389] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,391] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,400] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,400] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,401] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,401] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,402] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,404] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt... +7: [2023-04-28 00:09:47,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,406] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,408] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,409] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,410] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,414] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_07-model_00-model_states.pt. +7: [2023-04-28 00:09:47,423] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,553] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +5: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +2: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +1: [2023-04-28 00:09:47,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +3: [2023-04-28 00:09:47,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,557] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +4: [2023-04-28 00:09:47,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,559] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +5: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,562] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,562] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +0: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +2: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +4: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +1: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,565] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +3: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +0: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +6: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +6: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt... +7: [2023-04-28 00:09:47,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,573] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,574] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,575] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,576] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,576] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,579] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,580] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,581] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_08-model_00-model_states.pt. +7: [2023-04-28 00:09:47,584] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +6: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +3: [2023-04-28 00:09:47,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +2: [2023-04-28 00:09:47,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,635] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,636] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,639] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +2: [2023-04-28 00:09:47,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,640] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,640] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +6: [2023-04-28 00:09:47,641] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,641] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +4: [2023-04-28 00:09:47,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,642] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,642] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,643] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +3: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,644] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,645] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +4: [2023-04-28 00:09:47,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,646] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +1: [2023-04-28 00:09:47,647] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +5: [2023-04-28 00:09:47,649] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,650] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +5: [2023-04-28 00:09:47,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +0: [2023-04-28 00:09:47,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +1: [2023-04-28 00:09:47,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt... +7: [2023-04-28 00:09:47,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,668] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,671] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,672] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,676] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_09-model_00-model_states.pt. +7: [2023-04-28 00:09:47,681] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +2: [2023-04-28 00:09:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +2: [2023-04-28 00:09:47,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +5: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +3: [2023-04-28 00:09:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +7: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +6: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +1: [2023-04-28 00:09:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +0: [2023-04-28 00:09:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt... +4: [2023-04-28 00:09:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +1: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +5: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +3: [2023-04-28 00:09:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +6: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +4: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +0: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_10-model_00-model_states.pt. +7: [2023-04-28 00:09:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +1: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +4: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +7: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +6: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +2: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +5: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt... +2: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +3: [2023-04-28 00:09:47,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +1: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +4: [2023-04-28 00:09:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +0: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +5: [2023-04-28 00:09:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +7: [2023-04-28 00:09:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_11-model_00-model_states.pt. +6: [2023-04-28 00:09:47,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,962] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +4: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +6: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +7: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +2: [2023-04-28 00:09:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,967] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +4: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +7: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +2: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:47,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +1: [2023-04-28 00:09:47,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +1: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +0: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt... +5: [2023-04-28 00:09:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +5: [2023-04-28 00:09:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +6: [2023-04-28 00:09:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +3: [2023-04-28 00:09:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_12-model_00-model_states.pt. +0: [2023-04-28 00:09:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:48,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:48,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:48,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +2: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +6: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:48,079] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +4: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +0: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +3: [2023-04-28 00:09:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +1: [2023-04-28 00:09:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +7: [2023-04-28 00:09:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt... +5: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +7: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +5: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +4: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +1: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +2: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +0: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +3: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_13-model_00-model_states.pt. +6: [2023-04-28 00:09:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,178] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,178] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,179] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,179] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,180] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,180] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,181] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +5: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,182] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +3: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,183] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +6: [2023-04-28 00:09:48,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +7: [2023-04-28 00:09:48,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,184] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,184] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +4: [2023-04-28 00:09:48,185] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,185] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,186] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,187] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +7: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,188] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,189] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,189] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,190] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +0: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt... +2: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +1: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,191] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +5: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,192] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +3: [2023-04-28 00:09:48,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,193] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,193] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,194] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,195] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,195] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,196] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +6: [2023-04-28 00:09:48,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,196] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,197] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +2: [2023-04-28 00:09:48,198] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,198] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +4: [2023-04-28 00:09:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_14-model_00-model_states.pt. +0: [2023-04-28 00:09:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,308] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +6: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +2: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +1: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +5: [2023-04-28 00:09:48,309] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +7: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,310] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +0: [2023-04-28 00:09:48,311] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt... +4: [2023-04-28 00:09:48,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +5: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +2: [2023-04-28 00:09:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +6: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,318] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +1: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,319] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +3: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,320] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +0: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +4: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_15-model_00-model_states.pt. +7: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,323] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,325] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,416] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +3: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +7: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,417] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +1: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +6: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,418] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +5: [2023-04-28 00:09:48,419] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,419] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +4: [2023-04-28 00:09:48,420] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,421] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +0: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt... +2: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,422] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,423] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +3: [2023-04-28 00:09:48,425] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,424] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +7: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,426] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,427] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +5: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +2: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +1: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,428] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,429] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +6: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,430] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +0: [2023-04-28 00:09:48,431] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,431] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,432] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,432] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_16-model_00-model_states.pt. +4: [2023-04-28 00:09:48,433] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,436] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,506] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +7: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +5: [2023-04-28 00:09:48,508] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +0: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +4: [2023-04-28 00:09:48,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +6: [2023-04-28 00:09:48,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,511] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,512] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,513] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,514] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +1: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +2: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +1: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,515] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt... +3: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +3: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,516] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,517] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +5: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,518] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +0: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,519] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +6: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +4: [2023-04-28 00:09:48,520] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +7: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,521] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,522] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_17-model_00-model_states.pt. +2: [2023-04-28 00:09:48,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,523] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,524] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,525] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,526] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,528] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +6: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +0: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +6: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +5: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +7: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt... +3: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +3: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +4: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +2: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +1: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +7: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +5: [2023-04-28 00:09:48,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/layer_19-model_00-model_states.pt. +0: > overriding learning rate value to 0.0002 +0: > overriding minimum learning rate value to 2e-05 +0: > overriding warmup iterations value to 0 +0: > overriding total number of iterations value to 1 +0: > overriding decay style value to cosine +6: [2023-04-28 00:09:48,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +6: [2023-04-28 00:09:48,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +6: [2023-04-28 00:09:48,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +6: [2023-04-28 00:09:48,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +6: [2023-04-28 00:09:48,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +6: [2023-04-28 00:09:48,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +6: [2023-04-28 00:09:48,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +6: [2023-04-28 00:09:48,549] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +1: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +1: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +1: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +1: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +1: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +7: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +3: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +3: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +3: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +7: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +7: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +7: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +7: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +7: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +3: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +3: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +3: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +2: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +2: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +7: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +7: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +3: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +3: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +2: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +2: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +2: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +2: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +2: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +2: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +4: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +4: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +4: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +4: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +4: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +4: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +4: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +4: [2023-04-28 00:09:48,550] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +5: [2023-04-28 00:09:48,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +5: [2023-04-28 00:09:48,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +5: [2023-04-28 00:09:48,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +5: [2023-04-28 00:09:48,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +5: [2023-04-28 00:09:48,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +5: [2023-04-28 00:09:48,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +5: [2023-04-28 00:09:48,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +5: [2023-04-28 00:09:48,552] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +0: [2023-04-28 00:09:48,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2023-04-28 00:09:48,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2023-04-28 00:09:48,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2023-04-28 00:09:48,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2023-04-28 00:09:48,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2023-04-28 00:09:48,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2023-04-28 00:09:48,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +0: [2023-04-28 00:09:48,553] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +3: [2023-04-28 00:09:48,614] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +3: [2023-04-28 00:09:48,614] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 24 +3: [2023-04-28 00:09:48,616] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 24 +4: [2023-04-28 00:09:48,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +4: [2023-04-28 00:09:48,620] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 37 +4: [2023-04-28 00:09:48,622] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 37 +4: [2023-04-28 00:09:48,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +4: [2023-04-28 00:09:48,630] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 34 +1: [2023-04-28 00:09:48,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2023-04-28 00:09:48,631] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 15 +4: [2023-04-28 00:09:48,632] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 34 +1: [2023-04-28 00:09:48,633] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 15 +7: [2023-04-28 00:09:48,633] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +7: [2023-04-28 00:09:48,633] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 61 +7: [2023-04-28 00:09:48,634] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 61 +7: [2023-04-28 00:09:48,637] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +7: [2023-04-28 00:09:48,637] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 58 +1: [2023-04-28 00:09:48,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2023-04-28 00:09:48,638] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2023-04-28 00:09:48,638] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 9 +1: [2023-04-28 00:09:48,638] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 12 +7: [2023-04-28 00:09:48,639] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 58 +7: [2023-04-28 00:09:48,639] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +7: [2023-04-28 00:09:48,639] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 57 +1: [2023-04-28 00:09:48,640] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 9 +1: [2023-04-28 00:09:48,640] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 12 +7: [2023-04-28 00:09:48,640] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 57 +7: [2023-04-28 00:09:48,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +7: [2023-04-28 00:09:48,643] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 59 +4: [2023-04-28 00:09:48,643] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +4: [2023-04-28 00:09:48,643] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 35 +5: [2023-04-28 00:09:48,644] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +5: [2023-04-28 00:09:48,644] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 42 +7: [2023-04-28 00:09:48,645] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 59 +4: [2023-04-28 00:09:48,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +4: [2023-04-28 00:09:48,645] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 32 +4: [2023-04-28 00:09:48,645] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 35 +1: [2023-04-28 00:09:48,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +5: [2023-04-28 00:09:48,645] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +5: [2023-04-28 00:09:48,646] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 45 +1: [2023-04-28 00:09:48,646] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 8 +5: [2023-04-28 00:09:48,646] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 42 +4: [2023-04-28 00:09:48,647] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 32 +1: [2023-04-28 00:09:48,647] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 8 +5: [2023-04-28 00:09:48,648] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 45 +5: [2023-04-28 00:09:48,648] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +5: [2023-04-28 00:09:48,648] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 43 +5: [2023-04-28 00:09:48,650] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 43 +5: [2023-04-28 00:09:48,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +5: [2023-04-28 00:09:48,654] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 46 +6: [2023-04-28 00:09:48,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +6: [2023-04-28 00:09:48,654] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 48 +7: [2023-04-28 00:09:48,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +7: [2023-04-28 00:09:48,655] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 56 +5: [2023-04-28 00:09:48,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +5: [2023-04-28 00:09:48,655] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 41 +5: [2023-04-28 00:09:48,656] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 46 +6: [2023-04-28 00:09:48,656] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 48 +6: [2023-04-28 00:09:48,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +6: [2023-04-28 00:09:48,656] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 51 +7: [2023-04-28 00:09:48,657] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 56 +5: [2023-04-28 00:09:48,657] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 41 +2: [2023-04-28 00:09:48,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +2: [2023-04-28 00:09:48,657] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 21 +1: [2023-04-28 00:09:48,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2023-04-28 00:09:48,657] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 14 +6: [2023-04-28 00:09:48,658] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 51 +5: [2023-04-28 00:09:48,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +5: [2023-04-28 00:09:48,658] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 44 +2: [2023-04-28 00:09:48,659] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 21 +1: [2023-04-28 00:09:48,659] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 14 +3: [2023-04-28 00:09:48,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +3: [2023-04-28 00:09:48,659] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 30 +5: [2023-04-28 00:09:48,660] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 44 +1: [2023-04-28 00:09:48,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2023-04-28 00:09:48,660] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 13 +3: [2023-04-28 00:09:48,661] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 30 +2: [2023-04-28 00:09:48,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +2: [2023-04-28 00:09:48,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +2: [2023-04-28 00:09:48,661] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 18 +2: [2023-04-28 00:09:48,661] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 19 +4: [2023-04-28 00:09:48,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +4: [2023-04-28 00:09:48,662] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 36 +1: [2023-04-28 00:09:48,662] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 13 +2: [2023-04-28 00:09:48,663] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 19 +4: [2023-04-28 00:09:48,663] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 36 +2: [2023-04-28 00:09:48,664] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 18 +4: [2023-04-28 00:09:48,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +4: [2023-04-28 00:09:48,664] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 38 +6: [2023-04-28 00:09:48,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +6: [2023-04-28 00:09:48,665] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 49 +2: [2023-04-28 00:09:48,665] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +2: [2023-04-28 00:09:48,665] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 23 +4: [2023-04-28 00:09:48,666] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 38 +2: [2023-04-28 00:09:48,666] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +2: [2023-04-28 00:09:48,667] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 16 +7: [2023-04-28 00:09:48,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +2: [2023-04-28 00:09:48,667] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 23 +7: [2023-04-28 00:09:48,667] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 62 +4: [2023-04-28 00:09:48,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +4: [2023-04-28 00:09:48,667] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 39 +6: [2023-04-28 00:09:48,667] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 49 +6: [2023-04-28 00:09:48,667] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +6: [2023-04-28 00:09:48,667] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 50 +2: [2023-04-28 00:09:48,668] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 16 +7: [2023-04-28 00:09:48,668] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 62 +6: [2023-04-28 00:09:48,669] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 50 +4: [2023-04-28 00:09:48,669] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 39 +1: [2023-04-28 00:09:48,669] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2023-04-28 00:09:48,669] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 10 +6: [2023-04-28 00:09:48,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +6: [2023-04-28 00:09:48,670] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 53 +2: [2023-04-28 00:09:48,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +7: [2023-04-28 00:09:48,670] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +2: [2023-04-28 00:09:48,670] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 20 +7: [2023-04-28 00:09:48,670] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 63 +1: [2023-04-28 00:09:48,671] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 10 +2: [2023-04-28 00:09:48,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +2: [2023-04-28 00:09:48,671] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 22 +6: [2023-04-28 00:09:48,672] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 53 +2: [2023-04-28 00:09:48,671] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +7: [2023-04-28 00:09:48,672] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 63 +2: [2023-04-28 00:09:48,672] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 17 +4: [2023-04-28 00:09:48,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +4: [2023-04-28 00:09:48,672] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 33 +2: [2023-04-28 00:09:48,672] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 20 +6: [2023-04-28 00:09:48,672] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +6: [2023-04-28 00:09:48,672] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 55 +6: [2023-04-28 00:09:48,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +6: [2023-04-28 00:09:48,673] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 52 +2: [2023-04-28 00:09:48,673] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 22 +6: [2023-04-28 00:09:48,673] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +6: [2023-04-28 00:09:48,673] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 54 +4: [2023-04-28 00:09:48,674] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 33 +2: [2023-04-28 00:09:48,674] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 17 +6: [2023-04-28 00:09:48,674] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 55 +3: [2023-04-28 00:09:48,674] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +3: [2023-04-28 00:09:48,674] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 29 +6: [2023-04-28 00:09:48,674] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 52 +7: [2023-04-28 00:09:48,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +7: [2023-04-28 00:09:48,675] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 60 +6: [2023-04-28 00:09:48,675] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 54 +3: [2023-04-28 00:09:48,675] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +3: [2023-04-28 00:09:48,675] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 28 +3: [2023-04-28 00:09:48,676] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 29 +7: [2023-04-28 00:09:48,676] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 60 +3: [2023-04-28 00:09:48,677] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 28 +3: [2023-04-28 00:09:48,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +0: [2023-04-28 00:09:48,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +3: [2023-04-28 00:09:48,678] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 27 +0: [2023-04-28 00:09:48,679] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 7 +0: [2023-04-28 00:09:48,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +3: [2023-04-28 00:09:48,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +0: [2023-04-28 00:09:48,679] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 6 +3: [2023-04-28 00:09:48,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +3: [2023-04-28 00:09:48,679] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 25 +3: [2023-04-28 00:09:48,680] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 26 +3: [2023-04-28 00:09:48,681] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 27 +3: [2023-04-28 00:09:48,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +3: [2023-04-28 00:09:48,681] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 31 +0: [2023-04-28 00:09:48,681] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 7 +0: [2023-04-28 00:09:48,681] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 6 +3: [2023-04-28 00:09:48,681] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 25 +1: [2023-04-28 00:09:48,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +3: [2023-04-28 00:09:48,682] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 26 +1: [2023-04-28 00:09:48,682] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 11 +0: [2023-04-28 00:09:48,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2023-04-28 00:09:48,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2023-04-28 00:09:48,683] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 5 +0: [2023-04-28 00:09:48,683] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 4 +3: [2023-04-28 00:09:48,683] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 31 +1: [2023-04-28 00:09:48,683] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 11 +0: [2023-04-28 00:09:48,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2023-04-28 00:09:48,684] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 1 +0: [2023-04-28 00:09:48,685] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 5 +0: [2023-04-28 00:09:48,685] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 4 +0: [2023-04-28 00:09:48,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2023-04-28 00:09:48,686] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 3 +0: [2023-04-28 00:09:48,686] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 1 +0: [2023-04-28 00:09:48,688] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 3 +0: [2023-04-28 00:09:48,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2023-04-28 00:09:48,689] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 0 +0: [2023-04-28 00:09:48,690] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 0 +0: could not find arguments in the checkpoint ... +0: checkpoint version 3.0 +0: [2023-04-28 00:09:48,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2023-04-28 00:09:48,692] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 2 +0: [2023-04-28 00:09:48,693] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 2 +5: [2023-04-28 00:09:48,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +5: [2023-04-28 00:09:48,699] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 40 +5: [2023-04-28 00:09:48,701] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 40 +5: [2023-04-28 00:09:48,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_146m174b400m/global_step331103/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +5: [2023-04-28 00:09:48,710] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 64 ZeRO state_dicts for rank 47 +5: [2023-04-28 00:09:48,712] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 64 zero partition checkpoints for rank 47 +0: successfully loaded checkpoint from checkpoints_146m174b400m at iteration 0 +7: time (ms) | load-checkpoint: 2186.36 +0: estimated model parameters: 0.146525952 +0: estimated model parameters without embeddings: 0.106319616 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2023-04-28 00:09:49 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 1 +0: validation: 25600 +0: test: 25600 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.020766 seconds +0: number of documents: 28730568 +0: > dataset split: +0: train: +0: document indices in [0, 28730568) total of 28730568 documents +0: > loading doc-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_14B_text_document_train_indexmap_1ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_14B_text_document_train_indexmap_1ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_14B_text_document_train_indexmap_1ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.127 seconds +0: total number of samples: 6713794 +0: total number of epochs: 1 +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.049868 seconds +0: number of documents: 364608 +0: > dataset split: +0: validation: +0: document indices in [0, 364608) total of 364608 documents +0: > loading doc-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_25600ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_25600ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_25600ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.010 seconds +0: total number of samples: 84978 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2023-04-28 00:10:06 +0: done with setup ... +0: training ... +7: time (ms) | model-and-optimizer-setup: 19985.39 | train/valid/test-data-iterators-setup: 16931.85 +0: [after training is done] datetime: 2023-04-28 00:10:06 +7: ----------------------------------------------------------------------------------------------------------------- +7: validation loss at the end of training for val data | lm loss value: 3.277013E+00 | lm loss PPL: 2.649651E+01 | +7: ----------------------------------------------------------------------------------------------------------------- +END 3425869: Fri 28 Apr 2023 12:10:29 AM EEST