Hugging Face's logo

datablations
/
lm1-misc

TensorBoard
Model card Files Metrics Community
lm1-misc
File size: 91,427 Bytes 
f4bcf01
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
 
Model parameters: d_model 224 ffw_size 896 kv_size 32 n_heads 7 n_layers 4
Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 4 --hidden-size 224 --num-attention-heads 7 --kv-channels 32 --ffn-hidden-size 896 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 8 --global-batch-size 64 --train-samples 1 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-14m800m100mval --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 --override-lr-scheduler --no-load-optim --reset-progress --log-interval 10 --save-interval 1000 --eval-interval 1 --eval-iters 100 --tensorboard-dir tensorboard_14m800m100mval --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_14m800m100m --load checkpoints_14m800m100m --train-weighted-split-paths-path train100m.txt --valid-weighted-split-paths-path val.txt --data-impl mmap --deepspeed --deepspeed_config ds_configs/3423945.json --zero-stage 0
START 3423945: Thu 27 Apr 2023 04:39:56 PM EEST
0: 
0: 
0: ======================= ROCm System Management Interface =======================
0: ================================= Concise Info =================================
0: GPU  Temp   AvgPwr  SCLK    MCLK     Fan  Perf  PwrCap  VRAM%  GPU%  
0: 0    40.0c  92.0W   800Mhz  1600Mhz  0%   auto  560.0W    0%   0%    
0: 1    43.0c  N/A     800Mhz  1600Mhz  0%   auto  0.0W      0%   0%    
0: 2    39.0c  86.0W   800Mhz  1600Mhz  0%   auto  560.0W    0%   0%    
0: 3    45.0c  N/A     800Mhz  1600Mhz  0%   auto  0.0W      0%   0%    
0: 4    46.0c  84.0W   800Mhz  1600Mhz  0%   auto  560.0W    0%   0%    
0: 5    45.0c  N/A     800Mhz  1600Mhz  0%   auto  0.0W      0%   0%    
0: 6    38.0c  83.0W   800Mhz  1600Mhz  0%   auto  560.0W    0%   0%    
0: 7    45.0c  N/A     800Mhz  1600Mhz  0%   auto  0.0W      0%   0%    
0: ================================================================================
0: ============================= End of ROCm SMI Log ==============================
0: Launching on nid007308 (0/1), master nid007308 port 9999, GPUs 8, CUDA: True
0: using world size: 8, data-parallel-size: 8, 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 .............................. 8
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/3423945.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 ....................................... None
0:   evidence_data_path .............................. None
0:   exit_duration_in_mins ........................... None
0:   exit_interval ................................... None
0:   ffn_hidden_size ................................. 896
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 ............................... 64
0:   glu_activation .................................. None
0:   hidden_dropout .................................. 0.1
0:   hidden_size ..................................... 224
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-14m800m100mval
0:   kv_channels ..................................... 32
0:   layer_norm_fusion ............................... True
0:   layernorm_epsilon ............................... 1e-05
0:   lazy_mpu_init ................................... None
0:   load ............................................ checkpoints_14m800m100m
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 ................................ 8
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 ............................. 7
0:   num_channels .................................... 3
0:   num_classes ..................................... 1000
0:   num_layers ...................................... 4
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_14m800m100m
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_14m800m100mval
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_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 ...................................... 8
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: [2023-04-27 16:42:29,349] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
0: > setting tensorboard ...
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: 0.090 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: ninja: no work to do.
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: ninja: no work to do.
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_cuda.o layer_norm_hip_kernel.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: 9.463 seconds
0: time to initialize megatron (seconds): -48.665
0: [after megatron is initialized] datetime: 2023-04-27 16:42:39 
0: building GPT model ...
0: [2023-04-27 16:42:39,463] [INFO] [utils.py:827:see_memory_usage] Before Building Model
0: [2023-04-27 16:42:39,464] [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: [2023-04-27 16:42:39,464] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 38.2 GB, percent = 7.6%
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}
0: [2023-04-27 16:42:39,695] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer
0: stage=0 layers=11
0:      0: _to_float16
0:      1: EmbeddingPipe
0:      2: <lambda>
0:      3: ParallelTransformerLayerPipe
0:      4: ParallelTransformerLayerPipe
0:      5: ParallelTransformerLayerPipe
0:      6: ParallelTransformerLayerPipe
0:      7: undo
0:      8: MixedFusedLayerNorm
0:      9: EmbeddingPipe
0:     10: float16_to_fp32
0:   loss: CrossEntropy
0: [2023-04-27 16:42:39,927] [INFO] [utils.py:827:see_memory_usage] After Building Model
0: [2023-04-27 16:42:39,928] [INFO] [utils.py:828:see_memory_usage] MA 0.03 GB         Max_MA 0.03 GB         CA 0.05 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:39,928] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 38.22 GB, percent = 7.6%
0: setting training iterations to 0
0: > learning rate decay style: cosine
0: DeepSpeed is enabled.
0: [2023-04-27 16:42:39,929] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown
0: [2023-04-27 16:42:44,722] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False
0: [2023-04-27 16:42:44,722] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer
0: [2023-04-27 16:42:44,722] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer
0: [2023-04-27 16:42:44,723] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam
0: [2023-04-27 16:42:44,723] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer
0: [2023-04-27 16:42:44,839] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer
0: [2023-04-27 16:42:44,839] [INFO] [utils.py:828:see_memory_usage] MA 0.03 GB         Max_MA 0.03 GB         CA 0.05 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:44,840] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 40.76 GB, percent = 8.1%
0: ninja: no work to do.
0: Time to load utils op: 0.5941600799560547 seconds
0: Time to load utils op: 0.7109334468841553 seconds
0: Time to load utils op: 0.7100398540496826 seconds
0: Time to load utils op: 0.7110013961791992 seconds
0: Time to load utils op: 0.7101211547851562 seconds
0: Time to load utils op: 0.7113752365112305 secondsTime to load utils op: 0.7100043296813965 seconds
0: 
0: Time to load utils op: 0.7101755142211914 seconds
0: [2023-04-27 16:42:45,541] [INFO] [utils.py:827:see_memory_usage] before initializing group 0
0: [2023-04-27 16:42:45,542] [INFO] [utils.py:828:see_memory_usage] MA 0.03 GB         Max_MA 0.03 GB         CA 0.05 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:45,542] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 40.13 GB, percent = 8.0%
0: Time to load utils op: 0.003640890121459961 seconds
0: Time to load utils op: 0.0035970211029052734 secondsTime to load utils op: 0.003564596176147461 seconds
0: 
0: Time to load utils op: 0.0062711238861083984 seconds
0: Time to load utils op: 0.006462812423706055 seconds
0: Time to load utils op: 0.006939888000488281 secondsTime to load utils op: 0.006987333297729492 seconds
0: 
0: [2023-04-27 16:42:46,049] [INFO] [utils.py:827:see_memory_usage] after initializing group 0
0: [2023-04-27 16:42:46,050] [INFO] [utils.py:828:see_memory_usage] MA 0.08 GB         Max_MA 0.08 GB         CA 0.12 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:46,050] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 39.62 GB, percent = 7.9%
0: [2023-04-27 16:42:46,160] [INFO] [utils.py:827:see_memory_usage] before initializing group 1
0: [2023-04-27 16:42:46,161] [INFO] [utils.py:828:see_memory_usage] MA 0.08 GB         Max_MA 0.08 GB         CA 0.12 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:46,161] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 39.42 GB, percent = 7.8%
0: [2023-04-27 16:42:46,265] [INFO] [utils.py:827:see_memory_usage] after initializing group 1
0: [2023-04-27 16:42:46,265] [INFO] [utils.py:828:see_memory_usage] MA 0.09 GB         Max_MA 0.09 GB         CA 0.12 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:46,265] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 39.25 GB, percent = 7.8%
0: [2023-04-27 16:42:46,367] [INFO] [utils.py:827:see_memory_usage] before initializing group 2
0: [2023-04-27 16:42:46,368] [INFO] [utils.py:828:see_memory_usage] MA 0.09 GB         Max_MA 0.09 GB         CA 0.12 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:46,368] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 39.06 GB, percent = 7.8%
0: [2023-04-27 16:42:46,471] [INFO] [utils.py:827:see_memory_usage] after initializing group 2
0: [2023-04-27 16:42:46,471] [INFO] [utils.py:828:see_memory_usage] MA 0.09 GB         Max_MA 0.09 GB         CA 0.12 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:46,471] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 38.89 GB, percent = 7.7%
0: [2023-04-27 16:42:46,573] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer
0: [2023-04-27 16:42:46,573] [INFO] [utils.py:828:see_memory_usage] MA 0.09 GB         Max_MA 0.09 GB         CA 0.12 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:46,573] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 38.66 GB, percent = 7.7%
0: [2023-04-27 16:42:46,702] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer
0: [2023-04-27 16:42:46,703] [INFO] [utils.py:828:see_memory_usage] MA 0.1 GB         Max_MA 0.1 GB         CA 0.12 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:46,703] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 38.5 GB, percent = 7.7%
0: [2023-04-27 16:42:46,804] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer
0: [2023-04-27 16:42:46,804] [INFO] [utils.py:828:see_memory_usage] MA 0.1 GB         Max_MA 0.1 GB         CA 0.12 GB         Max_CA 0 GB 
0: [2023-04-27 16:42:46,805] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory:  used = 38.5 GB, percent = 7.7%
0: [2023-04-27 16:42:46,805] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam
0: [2023-04-27 16:42:46,805] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler
0: [2023-04-27 16:42:46,805] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = <megatron.learning_rates.AnnealingLR object at 0x14891b824b50>
0: [2023-04-27 16:42:46,805] [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: [2023-04-27 16:42:46,805] [INFO] [config.py:1007:print] DeepSpeedEngine configuration:
0: [2023-04-27 16:42:46,806] [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: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True}
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   amp_enabled .................. False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   amp_params ................... False
0: [2023-04-27 16:42:46,806] [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: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   bfloat16_enabled ............. True
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   checkpoint_parallel_write_pipeline  False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   checkpoint_tag_validation_enabled  True
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   checkpoint_tag_validation_fail  False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   comms_config ................. <deepspeed.comm.config.DeepSpeedCommsConfig object at 0x14891b824910>
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   communication_data_type ...... None
0: [2023-04-27 16:42:46,806] [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: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   curriculum_enabled ........... False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   curriculum_params ............ False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   dataloader_drop_last ......... False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   disable_allgather ............ False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   dump_state ................... False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   dynamic_loss_scale_args ...... None
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   eigenvalue_enabled ........... False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   eigenvalue_gas_boundary_resolution  1
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   eigenvalue_layer_name ........ bert.encoder.layer
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   eigenvalue_layer_num ......... 0
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   eigenvalue_max_iter .......... 100
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   eigenvalue_stability ......... 1e-06
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   eigenvalue_tol ............... 0.01
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   eigenvalue_verbose ........... False
0: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   elasticity_enabled ........... False
0: [2023-04-27 16:42:46,806] [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: [2023-04-27 16:42:46,806] [INFO] [config.py:1011:print]   fp16_auto_cast ............... None
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   fp16_enabled ................. False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   fp16_master_weights_and_gradients  False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   global_rank .................. 0
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   gradient_accumulation_steps .. 1
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   gradient_clipping ............ 1.0
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   gradient_predivide_factor .... 1.0
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   initial_dynamic_scale ........ 1
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   load_universal_checkpoint .... False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   loss_scale ................... 1.0
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   memory_breakdown ............. False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   monitor_config ............... <deepspeed.monitor.config.DeepSpeedMonitorConfig object at 0x14891b824880>
0: [2023-04-27 16:42:46,807] [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: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   optimizer_legacy_fusion ...... False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   optimizer_name ............... None
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   optimizer_params ............. None
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0}
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   pld_enabled .................. False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   pld_params ................... False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   prescale_gradients ........... False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   scheduler_name ............... None
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   scheduler_params ............. None
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   sparse_attention ............. None
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   sparse_gradients_enabled ..... False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   steps_per_print .............. 2000
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   train_batch_size ............. 64
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   train_micro_batch_size_per_gpu  8
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   use_node_local_storage ....... False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   wall_clock_breakdown ......... False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   world_size ................... 8
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   zero_allow_untested_optimizer  False
0: [2023-04-27 16:42:46,807] [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: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   zero_enabled ................. False
0: [2023-04-27 16:42:46,807] [INFO] [config.py:1011:print]   zero_optimization_stage ...... 0
0: [2023-04-27 16:42:46,807] [INFO] [config.py:996:print_user_config]   json = {
0:     "train_micro_batch_size_per_gpu": 8, 
0:     "train_batch_size": 64, 
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: 0.00041604042053222656 seconds
0: [2023-04-27 16:42:46,808] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=8
0: [2023-04-27 16:42:46,899] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=11 [0, 11) STAGE_PARAMS=14147392 (14.147M) TOTAL_PARAMS=14147392 (14.147M) UNIQUE_PARAMS=14147392 (14.147M)
0: [2023-04-27 16:42:46,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt...
0: [2023-04-27 16:42:46,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/mp_rank_00_model_states.pt.
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:46,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:47,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:47,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:47,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:47,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:47,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:47,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:47,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:47,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt...
0: [2023-04-27 16:42:47,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,059] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_01-model_00-model_states.pt.
0: [2023-04-27 16:42:47,062] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,063] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt...
0: [2023-04-27 16:42:47,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_03-model_00-model_states.pt.
0: [2023-04-27 16:42:47,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,104] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt...
0: [2023-04-27 16:42:47,105] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,106] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,107] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_04-model_00-model_states.pt.
0: [2023-04-27 16:42:47,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,108] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,133] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,133] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt...
0: [2023-04-27 16:42:47,134] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,135] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_05-model_00-model_states.pt.
0: [2023-04-27 16:42:47,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt...
0: [2023-04-27 16:42:47,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_06-model_00-model_states.pt.
0: [2023-04-27 16:42:47,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,169] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,170] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,170] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt...
0: [2023-04-27 16:42:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0:  > overriding learning rate value to 0.0002
0: [2023-04-27 16:42:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
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
0: [2023-04-27 16:42:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,171] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/layer_08-model_00-model_states.pt.
0: [2023-04-27 16:42:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt...
0: [2023-04-27 16:42:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt...
0: [2023-04-27 16:42:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt...
0: [2023-04-27 16:42:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt...
0: [2023-04-27 16:42:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt...
0: [2023-04-27 16:42:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt...
0: [2023-04-27 16:42:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt...
0: [2023-04-27 16:42:47,173] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt...
0: [2023-04-27 16:42:47,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt.
0: [2023-04-27 16:42:47,258] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 8 ZeRO state_dicts for rank 2
0: [2023-04-27 16:42:47,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt.
0: [2023-04-27 16:42:47,259] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 8 ZeRO state_dicts for rank 6
0: [2023-04-27 16:42:47,259] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 8 zero partition checkpoints for rank 2
0: [2023-04-27 16:42:47,260] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 8 zero partition checkpoints for rank 6
0: [2023-04-27 16:42:47,272] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt.
0: [2023-04-27 16:42:47,272] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 8 ZeRO state_dicts for rank 4
0: [2023-04-27 16:42:47,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt.
0: [2023-04-27 16:42:47,273] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 8 ZeRO state_dicts for rank 0
0: [2023-04-27 16:42:47,273] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 8 zero partition checkpoints for rank 4
0: [2023-04-27 16:42:47,273] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt.
0: [2023-04-27 16:42:47,274] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 8 ZeRO state_dicts for rank 3
0: [2023-04-27 16:42:47,275] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 8 zero partition checkpoints for rank 0
0: could not find arguments in the checkpoint ...
0:  checkpoint version 3.0
0: [2023-04-27 16:42:47,275] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 8 zero partition checkpoints for rank 3
0: [2023-04-27 16:42:47,276] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt.
0: [2023-04-27 16:42:47,276] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 8 ZeRO state_dicts for rank 5
0: [2023-04-27 16:42:47,277] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 8 zero partition checkpoints for rank 5
0: [2023-04-27 16:42:47,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt.
0: [2023-04-27 16:42:47,281] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 8 ZeRO state_dicts for rank 7
0: [2023-04-27 16:42:47,282] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 8 zero partition checkpoints for rank 7
0: [2023-04-27 16:42:47,324] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_14m800m100m/global_step1525/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt.
0: [2023-04-27 16:42:47,324] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 8 ZeRO state_dicts for rank 1
0: [2023-04-27 16:42:47,325] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 8 zero partition checkpoints for rank 1
0:   successfully loaded checkpoint from checkpoints_14m800m100m at iteration 0
0: time (ms) | load-checkpoint: 427.13
0: estimated model parameters: 0.014147392
0: estimated model parameters without embeddings: 0.002420544
0: [after model, optimizer, and learning rate scheduler are built] datetime: 2023-04-27 16:42:47 
0: > building train, validation, and test datasets ...
0:  > datasets target sizes (minimum size):
0:     train:      1
0:     validation: 6400
0:     test:       6400
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 0.045871 seconds
0:     number of documents: 208931
0:  > dataset split:
0:     train:
0:      document indices in [0, 208931) total of 208931 documents
0:  > loading doc-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_100M_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_100M_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_100M_text_document_train_indexmap_1ns_2048sl_1234s_shuffle_idx.npy
0:     loaded indexed file in 0.103 seconds
0:     total number of samples: 48805
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 0.113429 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_6400ns_2048sl_1234s_doc_idx.npy
0:  > loading sample-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_6400ns_2048sl_1234s_sample_idx.npy
0:  > loading shuffle-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_6400ns_2048sl_1234s_shuffle_idx.npy
0:     loaded indexed file in 0.112 seconds
0:     total number of samples: 84978
0:     total number of epochs: 1
0: > finished creating GPT datasets ...
0: time (ms) | model-and-optimizer-setup: 8565.33 | train/valid/test-data-iterators-setup: 7570.00
0: [after dataloaders are built] datetime: 2023-04-27 16:42:55 
0: done with setup ...
0: training ...
0: [after training is done] datetime: 2023-04-27 16:42:55 
0: -----------------------------------------------------------------------------------------------------------------
0: validation loss at the end of training for val data | lm loss value: 5.816824E+00 | lm loss PPL: 3.359037E+02 | 
0: -----------------------------------------------------------------------------------------------------------------
END 3423945: Thu 27 Apr 2023 04:43:29 PM EEST