File size: 24,834 Bytes
f9fc05c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 |
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 84_762_549 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --loss-scale 12 --clip-grad 1.0 --kill-switch-path kill-switch-146m174b100m --bf16 --checkpoint-activations --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 84_762_549 --lr-warmup-samples 847_625 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 100 --save-interval 10000 --eval-interval 10000 --eval-iters 1 --tensorboard-dir tensorboard_146m174b100m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_146m174b100m --load checkpoints_146m174b100m --train-weighted-split-paths-path train100m.txt --valid-weighted-split-paths-path val.txt --data-impl mmap --deepspeed --deepspeed_config ds_configs/3319491.json --zero-stage 0
START 3319491: Fri 17 Mar 2023 01:50:53 PM EET
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 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
0: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
0: 4 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
0: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
0: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
0: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
0: ================================================================================
0: ============================= 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 45.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
7: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
7: 2 38.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
7: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
7: 4 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
7: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
7: 6 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
7: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
7: ================================================================================
7: ============================= 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 45.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
1: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
1: 2 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
1: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
1: 4 49.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
1: 5 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
1: 6 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
1: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
1: ================================================================================
1: ============================= 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 49.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
4: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
4: 2 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
4: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
4: 4 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
4: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
4: 6 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
4: 7 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
4: ================================================================================
4: ============================= 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 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
5: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
5: 2 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
5: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
5: 4 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
5: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
5: 6 35.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
5: 7 40.0c 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 46.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
3: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
3: 2 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
3: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
3: 4 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
3: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
3: 6 47.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
3: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
3: ================================================================================
3: ============================= 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 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
2: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
2: 2 40.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
2: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
2: 4 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
2: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
2: 6 40.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
2: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
2: ================================================================================
2: ============================= 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 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
6: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
6: 2 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
6: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
6: 4 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
6: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
6: 6 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0%
6: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0%
6: ================================================================================
6: ============================= End of ROCm SMI Log ==============================
7: Launching on nid006946 (7/8), master nid006939 port 9999, GPUs 8, CUDA: True
4: Launching on nid006943 (4/8), master nid006939 port 9999, GPUs 8, CUDA: True
6: Launching on nid006945 (6/8), master nid006939 port 9999, GPUs 8, CUDA: True
3: Launching on nid006942 (3/8), master nid006939 port 9999, GPUs 8, CUDA: True
0: Launching on nid006939 (0/8), master nid006939 port 9999, GPUs 8, CUDA: True
5: Launching on nid006944 (5/8), master nid006939 port 9999, GPUs 8, CUDA: True
1: Launching on nid006940 (1/8), master nid006939 port 9999, GPUs 8, CUDA: True
2: Launching on nid006941 (2/8), master nid006939 port 9999, GPUs 8, CUDA: True
7: > setting tensorboard ...
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 .......................... True
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/3319491.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 ................................... 10000
0: eval_iters ...................................... 1
0: eval_only ....................................... None
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-146m174b100m
0: kv_channels ..................................... 64
0: layer_norm_fusion ............................... True
0: layernorm_epsilon ............................... 1e-05
0: lazy_mpu_init ................................... None
0: load ............................................ checkpoints_146m174b100m
0: local_rank ...................................... None
0: log_batch_size_to_tensorboard ................... True
0: log_interval .................................... 100
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 ...................................... 12.0
0: loss_scale_window ............................... 1000
0: lr .............................................. 0.0002
0: lr_decay_iters .................................. None
0: lr_decay_samples ................................ 84762549
0: lr_decay_style .................................. cosine
0: lr_decay_tokens ................................. None
0: lr_warmup_fraction .............................. None
0: lr_warmup_iters ................................. 0
0: lr_warmup_samples ............................... 847625
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 ................................... None
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 ........................... False
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 .................................. None
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_146m174b100m
0: save_interval ................................... 10000
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_146m174b100m
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 ................................... 84762549
0: train_tokens .................................... None
0: train_weighted_split_names ...................... ['train']
0: train_weighted_split_paths ...................... [['/scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_100M_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
0: **** Git info for Megatron: git_hash=unknown git_branch=unknown ****
0: > initializing torch distributed ...
0: [2023-03-17 13:53:41,482] [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: 0.065 seconds
0: > compiling and loading fused kernels ...
|