Hugging Face's logo

iamketan25
/
gpt-neo-1.3b-sft_epoch2

Text Generation
Transformers
PyTorch
gpt_neo
Model card Files Community
1
gpt-neo-1.3b-sft_epoch2
File size: 146,210 Bytes 
18f5e6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
 
[2023-04-19 16:55:10,332] [WARNING] [runner.py:190:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only.
[2023-04-19 16:55:10,380] [INFO] [runner.py:540:main] cmd = /home/ubuntu/miniconda3/bin/python -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMCwgMSwgMiwgM119 --master_addr=127.0.0.1 --master_port=29500 --enable_each_rank_log=None main.py --data_path iamketan25/alpaca-instructions-dataset iamketan25/dolly-instructions-15k iamketan25/gsm-general-qa-instructions --model_name_or_path iamketan25/gpt-neo-1.3b-sft --per_device_train_batch_size 4 --per_device_eval_batch_size 4 --max_seq_len 512 --learning_rate 1e-3 --weight_decay 0.1 --num_train_epochs 1 --gradient_accumulation_steps 2 --lr_scheduler_type cosine --num_warmup_steps 0 --seed 1234 --zero_stage 3 --lora_dim 16 --lora_module_name h. --only_optimize_lora --deepspeed --output_dir ./gpt_neo_1.3b_sft_lora_dim_32_zero_stage3_epoch2
[2023-04-19 16:55:12,124] [INFO] [launch.py:229:main] WORLD INFO DICT: {'localhost': [0, 1, 2, 3]}
[2023-04-19 16:55:12,124] [INFO] [launch.py:235:main] nnodes=1, num_local_procs=4, node_rank=0
[2023-04-19 16:55:12,124] [INFO] [launch.py:246:main] global_rank_mapping=defaultdict(<class 'list'>, {'localhost': [0, 1, 2, 3]})
[2023-04-19 16:55:12,124] [INFO] [launch.py:247:main] dist_world_size=4
[2023-04-19 16:55:12,124] [INFO] [launch.py:249:main] Setting CUDA_VISIBLE_DEVICES=0,1,2,3
[2023-04-19 16:55:15,363] [INFO] [comm.py:586:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
[2023-04-19 16:55:20,249] [INFO] [partition_parameters.py:436:__exit__] finished initializing model with 1.42B parameters
Some weights of GPTNeoForCausalLM were not initialized from the model checkpoint at iamketan25/gpt-neo-1.3b-sft and are newly initialized: ['transformer.h.10.attn.attention.masked_bias', 'transformer.h.9.attn.attention.masked_bias', 'transformer.h.17.attn.attention.masked_bias', 'transformer.h.1.attn.attention.masked_bias', 'transformer.h.12.attn.attention.masked_bias', 'transformer.h.16.attn.attention.masked_bias', 'transformer.h.11.attn.attention.masked_bias', 'transformer.h.6.attn.attention.masked_bias', 'transformer.h.4.attn.attention.masked_bias', 'transformer.h.20.attn.attention.masked_bias', 'transformer.h.14.attn.attention.masked_bias', 'transformer.h.13.attn.attention.masked_bias', 'transformer.h.8.attn.attention.masked_bias', 'transformer.h.7.attn.attention.masked_bias', 'transformer.h.3.attn.attention.masked_bias', 'transformer.h.23.attn.attention.masked_bias', 'transformer.h.18.attn.attention.masked_bias', 'transformer.h.2.attn.attention.masked_bias', 'transformer.h.0.attn.attention.masked_bias', 'transformer.h.5.attn.attention.masked_bias', 'transformer.h.22.attn.attention.masked_bias', 'transformer.h.19.attn.attention.masked_bias', 'transformer.h.21.attn.attention.masked_bias', 'transformer.h.15.attn.attention.masked_bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
Some weights of GPTNeoForCausalLM were not initialized from the model checkpoint at iamketan25/gpt-neo-1.3b-sft and are newly initialized: ['transformer.h.20.attn.attention.masked_bias', 'transformer.h.12.attn.attention.masked_bias', 'transformer.h.15.attn.attention.masked_bias', 'transformer.h.5.attn.attention.masked_bias', 'transformer.h.3.attn.attention.masked_bias', 'transformer.h.7.attn.attention.masked_bias', 'transformer.h.16.attn.attention.masked_bias', 'transformer.h.4.attn.attention.masked_bias', 'transformer.h.9.attn.attention.masked_bias', 'transformer.h.11.attn.attention.masked_bias', 'transformer.h.19.attn.attention.masked_bias', 'transformer.h.2.attn.attention.masked_bias', 'transformer.h.14.attn.attention.masked_bias', 'transformer.h.8.attn.attention.masked_bias', 'transformer.h.18.attn.attention.masked_bias', 'transformer.h.22.attn.attention.masked_bias', 'transformer.h.0.attn.attention.masked_bias', 'transformer.h.21.attn.attention.masked_bias', 'transformer.h.1.attn.attention.masked_bias', 'transformer.h.17.attn.attention.masked_bias', 'transformer.h.6.attn.attention.masked_bias', 'transformer.h.23.attn.attention.masked_bias', 'transformer.h.10.attn.attention.masked_bias', 'transformer.h.13.attn.attention.masked_bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
Some weights of GPTNeoForCausalLM were not initialized from the model checkpoint at iamketan25/gpt-neo-1.3b-sft and are newly initialized: ['transformer.h.13.attn.attention.masked_bias', 'transformer.h.7.attn.attention.masked_bias', 'transformer.h.0.attn.attention.masked_bias', 'transformer.h.2.attn.attention.masked_bias', 'transformer.h.10.attn.attention.masked_bias', 'transformer.h.4.attn.attention.masked_bias', 'transformer.h.23.attn.attention.masked_bias', 'transformer.h.6.attn.attention.masked_bias', 'transformer.h.15.attn.attention.masked_bias', 'transformer.h.16.attn.attention.masked_bias', 'transformer.h.18.attn.attention.masked_bias', 'transformer.h.5.attn.attention.masked_bias', 'transformer.h.3.attn.attention.masked_bias', 'transformer.h.1.attn.attention.masked_bias', 'transformer.h.11.attn.attention.masked_bias', 'transformer.h.9.attn.attention.masked_bias', 'transformer.h.19.attn.attention.masked_bias', 'transformer.h.8.attn.attention.masked_bias', 'transformer.h.17.attn.attention.masked_bias', 'transformer.h.20.attn.attention.masked_bias', 'transformer.h.21.attn.attention.masked_bias', 'transformer.h.22.attn.attention.masked_bias', 'transformer.h.12.attn.attention.masked_bias', 'transformer.h.14.attn.attention.masked_bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
Some weights of GPTNeoForCausalLM were not initialized from the model checkpoint at iamketan25/gpt-neo-1.3b-sft and are newly initialized: ['transformer.h.18.attn.attention.masked_bias', 'transformer.h.10.attn.attention.masked_bias', 'transformer.h.13.attn.attention.masked_bias', 'transformer.h.4.attn.attention.masked_bias', 'transformer.h.20.attn.attention.masked_bias', 'transformer.h.21.attn.attention.masked_bias', 'transformer.h.15.attn.attention.masked_bias', 'transformer.h.7.attn.attention.masked_bias', 'transformer.h.2.attn.attention.masked_bias', 'transformer.h.14.attn.attention.masked_bias', 'transformer.h.6.attn.attention.masked_bias', 'transformer.h.1.attn.attention.masked_bias', 'transformer.h.9.attn.attention.masked_bias', 'transformer.h.11.attn.attention.masked_bias', 'transformer.h.12.attn.attention.masked_bias', 'transformer.h.5.attn.attention.masked_bias', 'transformer.h.17.attn.attention.masked_bias', 'transformer.h.16.attn.attention.masked_bias', 'transformer.h.22.attn.attention.masked_bias', 'transformer.h.0.attn.attention.masked_bias', 'transformer.h.8.attn.attention.masked_bias', 'transformer.h.19.attn.attention.masked_bias', 'transformer.h.23.attn.attention.masked_bias', 'transformer.h.3.attn.attention.masked_bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--alpaca-instructions-dataset-57eb880093a82a29/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 744.40it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--alpaca-instructions-dataset-57eb880093a82a29/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 800.97it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--alpaca-instructions-dataset-57eb880093a82a29/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 802.12it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--alpaca-instructions-dataset-57eb880093a82a29/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 803.74it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--dolly-instructions-15k-4899fa89efa5cbf6/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 1080.87it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--dolly-instructions-15k-4899fa89efa5cbf6/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 1050.28it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--dolly-instructions-15k-4899fa89efa5cbf6/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 1057.57it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--dolly-instructions-15k-4899fa89efa5cbf6/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|█████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 1041.67it/s]
Downloading and preparing dataset parquet/iamketan25--gsm-general-qa-instructions to /home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--gsm-general-qa-instructions-013277d5a826dcd4/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec...

Downloading data files:   0%|                                                                       | 0/2 [00:00<?, ?it/s]

Downloading data:   0%|                                                                       | 0.00/8.56M [00:00<?, ?B/s]Downloading data: 100%|██████████████████████████████████████████████████████████████| 8.56M/8.56M [00:00<00:00, 90.5MB/s]

Downloading data files:  50%|███████████████████████████████▌                               | 1/2 [00:00<00:00,  3.94it/s]

Downloading data:   0%|                                                                        | 0.00/967k [00:00<?, ?B/s]Downloading data: 100%|████████████████████████████████████████████████████████████████| 967k/967k [00:00<00:00, 33.7MB/s]

Downloading data files: 100%|███████████████████████████████████████████████████████████████| 2/2 [00:00<00:00,  4.63it/s]
Downloading data files: 100%|███████████████████████████████████████████████████████████████| 2/2 [00:00<00:00,  4.51it/s]

Extracting data files:   0%|                                                                        | 0/2 [00:00<?, ?it/s]
Extracting data files: 100%|██████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 2247.15it/s]

Generating train split: 0 examples [00:00, ? examples/s]
                                                        

Generating test split: 0 examples [00:00, ? examples/s]
                                                       
Dataset parquet downloaded and prepared to /home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--gsm-general-qa-instructions-013277d5a826dcd4/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec. Subsequent calls will reuse this data.

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 969.45it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--gsm-general-qa-instructions-013277d5a826dcd4/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 622.16it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--gsm-general-qa-instructions-013277d5a826dcd4/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 895.74it/s]
Found cached dataset parquet (/home/ubuntu/.cache/huggingface/datasets/iamketan25___parquet/iamketan25--gsm-general-qa-instructions-013277d5a826dcd4/0.0.0/2a3b91fbd88a2c90d1dbbb32b460cf621d31bd5b05b934492fdef7d8d6f236ec)

  0%|                                                                                               | 0/2 [00:00<?, ?it/s]
100%|██████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 859.58it/s]
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
Detected CUDA files, patching ldflags
Emitting ninja build file /home/ubuntu/.cache/torch_extensions/py39_cu117/fused_adam/build.ninja...
Building extension module fused_adam...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
ninja: no work to do.
Loading extension module fused_adam...
Time to load fused_adam op: 0.5939269065856934 seconds
Loading extension module fused_adam...
Time to load fused_adam op: 0.6027216911315918 seconds
Loading extension module fused_adam...
Time to load fused_adam op: 0.6026906967163086 seconds
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
Detected CUDA files, patching ldflags
Emitting ninja build file /home/ubuntu/.cache/torch_extensions/py39_cu117/fused_adam/build.ninja...
Building extension module fused_adam...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
ninja: no work to do.
Loading extension module fused_adam...
Time to load fused_adam op: 1.034358024597168 seconds
[2023-04-19 16:57:05,669] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed info: version=0.9.0, git-hash=unknown, git-branch=unknown
[2023-04-19 16:57:05,675] [INFO] [comm.py:580:init_distributed] Distributed backend already initialized
[2023-04-19 16:57:05,871] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False
[2023-04-19 16:57:05,873] [INFO] [logging.py:96:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer
[2023-04-19 16:57:05,873] [INFO] [logging.py:96:log_dist] [Rank 0] Using client Optimizer as basic optimizer
[2023-04-19 16:57:05,893] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam
[2023-04-19 16:57:05,893] [INFO] [utils.py:51:is_zero_supported_optimizer] Checking ZeRO support for optimizer=FusedAdam type=<class 'deepspeed.ops.adam.fused_adam.FusedAdam'>
[2023-04-19 16:57:05,894] [INFO] [logging.py:96:log_dist] [Rank 0] Creating torch.float16 ZeRO stage 3 optimizer
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
Emitting ninja build file /home/ubuntu/.cache/torch_extensions/py39_cu117/utils/build.ninja...
Building extension module utils...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[2023-04-19 16:57:06,328] [INFO] [utils.py:785:see_memory_usage] Stage 3 initialize beginning
[2023-04-19 16:57:06,329] [INFO] [utils.py:786:see_memory_usage] MA 0.78 GB         Max_MA 1.28 GB         CA 3.41 GB         Max_CA 3 GB 
[2023-04-19 16:57:06,329] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.22 GB, percent = 18.9%
[2023-04-19 16:57:06,331] [INFO] [stage3.py:113:__init__] Reduce bucket size 500,000,000
[2023-04-19 16:57:06,331] [INFO] [stage3.py:114:__init__] Prefetch bucket size 30000000
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
	- Avoid using `tokenizers` before the fork if possible
	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
ninja: no work to do.
Loading extension module utils...
Time to load utils op: 0.5918192863464355 seconds
Loading extension module utils...
Loading extension module utils...
Time to load utils op: 0.6023216247558594 seconds
Time to load utils op: 0.6022861003875732 seconds
Loading extension module utils...
Time to load utils op: 0.20152544975280762 seconds
[2023-04-19 16:57:06,875] [INFO] [utils.py:785:see_memory_usage] DeepSpeedZeRoOffload initialize [begin]
[2023-04-19 16:57:06,876] [INFO] [utils.py:786:see_memory_usage] MA 0.78 GB         Max_MA 0.78 GB         CA 3.41 GB         Max_CA 3 GB 
[2023-04-19 16:57:06,876] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.23 GB, percent = 18.9%
Parameter Offload: Total persistent parameters: 495616 in 170 params
[2023-04-19 16:57:07,289] [INFO] [utils.py:785:see_memory_usage] DeepSpeedZeRoOffload initialize [end]
[2023-04-19 16:57:07,289] [INFO] [utils.py:786:see_memory_usage] MA 0.76 GB         Max_MA 0.78 GB         CA 3.41 GB         Max_CA 3 GB 
[2023-04-19 16:57:07,290] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.23 GB, percent = 18.9%
[2023-04-19 16:57:07,630] [INFO] [utils.py:785:see_memory_usage] Before creating fp16 partitions
[2023-04-19 16:57:07,631] [INFO] [utils.py:786:see_memory_usage] MA 0.76 GB         Max_MA 0.76 GB         CA 3.41 GB         Max_CA 3 GB 
[2023-04-19 16:57:07,631] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.23 GB, percent = 18.9%
[2023-04-19 16:57:08,444] [INFO] [utils.py:785:see_memory_usage] After creating fp16 partitions: 1
[2023-04-19 16:57:08,444] [INFO] [utils.py:786:see_memory_usage] MA 0.76 GB         Max_MA 0.76 GB         CA 1.67 GB         Max_CA 3 GB 
[2023-04-19 16:57:08,444] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.25 GB, percent = 18.9%
[2023-04-19 16:57:08,786] [INFO] [utils.py:785:see_memory_usage] Before creating fp32 partitions
[2023-04-19 16:57:08,786] [INFO] [utils.py:786:see_memory_usage] MA 0.76 GB         Max_MA 0.76 GB         CA 1.67 GB         Max_CA 2 GB 
[2023-04-19 16:57:08,787] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.25 GB, percent = 18.9%
[2023-04-19 16:57:09,128] [INFO] [utils.py:785:see_memory_usage] After creating fp32 partitions
[2023-04-19 16:57:09,128] [INFO] [utils.py:786:see_memory_usage] MA 0.77 GB         Max_MA 0.78 GB         CA 1.67 GB         Max_CA 2 GB 
[2023-04-19 16:57:09,129] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.25 GB, percent = 18.9%
[2023-04-19 16:57:09,469] [INFO] [utils.py:785:see_memory_usage] Before initializing optimizer states
[2023-04-19 16:57:09,470] [INFO] [utils.py:786:see_memory_usage] MA 0.77 GB         Max_MA 0.77 GB         CA 1.67 GB         Max_CA 2 GB 
[2023-04-19 16:57:09,470] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.25 GB, percent = 18.9%
[2023-04-19 16:57:09,810] [INFO] [utils.py:785:see_memory_usage] After initializing optimizer states
[2023-04-19 16:57:09,811] [INFO] [utils.py:786:see_memory_usage] MA 0.8 GB         Max_MA 0.81 GB         CA 1.67 GB         Max_CA 2 GB 
[2023-04-19 16:57:09,811] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.25 GB, percent = 18.9%
[2023-04-19 16:57:09,812] [INFO] [stage3.py:366:_setup_for_real_optimizer] optimizer state initialized
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
No modifications detected for re-loaded extension module utils, skipping build step...
Loading extension module utils...
Time to load utils op: 0.00035953521728515625 seconds
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
No modifications detected for re-loaded extension module utils, skipping build step...
Loading extension module utils...
Time to load utils op: 0.00038123130798339844 seconds
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
No modifications detected for re-loaded extension module utils, skipping build step...
Loading extension module utils...
Time to load utils op: 0.0003180503845214844 seconds
[2023-04-19 16:57:10,317] [INFO] [utils.py:785:see_memory_usage] After initializing ZeRO optimizer
[2023-04-19 16:57:10,317] [INFO] [utils.py:786:see_memory_usage] MA 1.74 GB         Max_MA 1.74 GB         CA 2.61 GB         Max_CA 3 GB 
[2023-04-19 16:57:10,318] [INFO] [utils.py:793:see_memory_usage] CPU Virtual Memory:  used = 35.25 GB, percent = 18.9%
[2023-04-19 16:57:10,318] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam
[2023-04-19 16:57:10,318] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed using client LR scheduler
[2023-04-19 16:57:10,318] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed LR Scheduler = <torch.optim.lr_scheduler.LambdaLR object at 0x7f66ae604310>
[2023-04-19 16:57:10,318] [INFO] [logging.py:96:log_dist] [Rank 0] step=0, skipped=0, lr=[0.001], mom=[(0.9, 0.95)]
[2023-04-19 16:57:10,319] [INFO] [config.py:953:print] DeepSpeedEngine configuration:
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   activation_checkpointing_config  {
    "partition_activations": false, 
    "contiguous_memory_optimization": false, 
    "cpu_checkpointing": false, 
    "number_checkpoints": null, 
    "synchronize_checkpoint_boundary": false, 
    "profile": false
}
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True}
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   amp_enabled .................. False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   amp_params ................... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   autotuning_config ............ {
    "enabled": false, 
    "start_step": null, 
    "end_step": null, 
    "metric_path": null, 
    "arg_mappings": null, 
    "metric": "throughput", 
    "model_info": null, 
    "results_dir": "autotuning_results", 
    "exps_dir": "autotuning_exps", 
    "overwrite": true, 
    "fast": true, 
    "start_profile_step": 3, 
    "end_profile_step": 5, 
    "tuner_type": "gridsearch", 
    "tuner_early_stopping": 5, 
    "tuner_num_trials": 50, 
    "model_info_path": null, 
    "mp_size": 1, 
    "max_train_batch_size": null, 
    "min_train_batch_size": 1, 
    "max_train_micro_batch_size_per_gpu": 1.024000e+03, 
    "min_train_micro_batch_size_per_gpu": 1, 
    "num_tuning_micro_batch_sizes": 3
}
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   bfloat16_enabled ............. False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   checkpoint_parallel_write_pipeline  False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   checkpoint_tag_validation_enabled  True
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   checkpoint_tag_validation_fail  False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   comms_config ................. <deepspeed.comm.config.DeepSpeedCommsConfig object at 0x7f66f708c490>
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   communication_data_type ...... None
[2023-04-19 16:57:10,320] [INFO] [config.py:957: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_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}}
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   curriculum_enabled_legacy .... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   curriculum_params_legacy ..... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   data_efficiency_config ....... {'enabled': False, 'seed': 1234, 'data_sampling': {'enabled': False, 'num_epochs': 1000, 'num_workers': 0, 'curriculum_learning': {'enabled': False}}, 'data_routing': {'enabled': False, 'random_ltd': {'enabled': False, 'layer_token_lr_schedule': {'enabled': False}}}}
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   data_efficiency_enabled ...... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   dataloader_drop_last ......... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   disable_allgather ............ False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   dump_state ................... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   dynamic_loss_scale_args ...... {'init_scale': 65536, 'scale_window': 100, 'delayed_shift': 2, 'min_scale': 1}
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   eigenvalue_enabled ........... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   eigenvalue_gas_boundary_resolution  1
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   eigenvalue_layer_name ........ bert.encoder.layer
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   eigenvalue_layer_num ......... 0
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   eigenvalue_max_iter .......... 100
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   eigenvalue_stability ......... 1e-06
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   eigenvalue_tol ............... 0.01
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   eigenvalue_verbose ........... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   elasticity_enabled ........... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   flops_profiler_config ........ {
    "enabled": false, 
    "profile_step": 1, 
    "module_depth": -1, 
    "top_modules": 1, 
    "detailed": true, 
    "output_file": null
}
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   fp16_auto_cast ............... False
[2023-04-19 16:57:10,320] [INFO] [config.py:957:print]   fp16_enabled ................. True
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   fp16_master_weights_and_gradients  False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   global_rank .................. 0
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   grad_accum_dtype ............. None
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   gradient_accumulation_steps .. 2
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   gradient_clipping ............ 1.0
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   gradient_predivide_factor .... 1.0
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   hybrid_engine ................ enabled=False max_out_tokens=512 inference_tp_size=1 release_inference_cache=False pin_parameters=True tp_gather_partition_size=8
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   initial_dynamic_scale ........ 65536
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   load_universal_checkpoint .... False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   loss_scale ................... 0
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   memory_breakdown ............. False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   monitor_config ............... tensorboard=TensorBoardConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') wandb=WandbConfig(enabled=False, group=None, team=None, project='deepspeed') csv_monitor=CSVConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') enabled=False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   nebula_config ................ {
    "enabled": false, 
    "persistent_storage_path": null, 
    "persistent_time_interval": 100, 
    "num_of_version_in_retention": 2, 
    "enable_nebula_load": true, 
    "load_path": null
}
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   optimizer_legacy_fusion ...... False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   optimizer_name ............... None
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   optimizer_params ............. None
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0}
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   pld_enabled .................. False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   pld_params ................... False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   prescale_gradients ........... False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   scheduler_name ............... None
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   scheduler_params ............. None
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   sparse_attention ............. None
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   sparse_gradients_enabled ..... False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   steps_per_print .............. 10
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   train_batch_size ............. 32
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   train_micro_batch_size_per_gpu  4
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   use_node_local_storage ....... False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   wall_clock_breakdown ......... False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   world_size ................... 4
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   zero_allow_untested_optimizer  False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   zero_config .................. stage=3 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500,000,000 allgather_partitions=True allgather_bucket_size=500,000,000 overlap_comm=True load_from_fp32_weights=True elastic_checkpoint=False offload_param=DeepSpeedZeroOffloadParamConfig(device='none', nvme_path=None, buffer_count=5, buffer_size=100,000,000, max_in_cpu=1,000,000,000, pin_memory=False) offload_optimizer=DeepSpeedZeroOffloadOptimizerConfig(device='none', nvme_path=None, buffer_count=4, pin_memory=False, pipeline=False, pipeline_read=False, pipeline_write=False, fast_init=False) sub_group_size=1,000,000,000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=30000000 param_persistence_threshold=10000 model_persistence_threshold=sys.maxsize max_live_parameters=30000000 max_reuse_distance=1,000,000,000 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 memory_efficient_linear=False
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   zero_enabled ................. True
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   zero_force_ds_cpu_optimizer .. True
[2023-04-19 16:57:10,321] [INFO] [config.py:957:print]   zero_optimization_stage ...... 3
[2023-04-19 16:57:10,321] [INFO] [config.py:943:print_user_config]   json = {
    "train_batch_size": 32, 
    "train_micro_batch_size_per_gpu": 4, 
    "steps_per_print": 10, 
    "zero_optimization": {
        "stage": 3, 
        "offload_param": {
            "device": "none"
        }, 
        "offload_optimizer": {
            "device": "none"
        }, 
        "stage3_param_persistence_threshold": 1.000000e+04, 
        "stage3_max_live_parameters": 3.000000e+07, 
        "stage3_prefetch_bucket_size": 3.000000e+07, 
        "memory_efficient_linear": false
    }, 
    "fp16": {
        "enabled": true, 
        "loss_scale_window": 100
    }, 
    "gradient_clipping": 1.0, 
    "prescale_gradients": false, 
    "wall_clock_breakdown": false, 
    "hybrid_engine": {
        "enabled": false, 
        "inference_tp_size": 1, 
        "release_inference_cache": false, 
        "pin_parameters": true, 
        "tp_gather_partition_size": 8
    }
}
Using /home/ubuntu/.cache/torch_extensions/py39_cu117 as PyTorch extensions root...
No modifications detected for re-loaded extension module utils, skipping build step...
Loading extension module utils...
Time to load utils op: 0.0003190040588378906 seconds
***** Running training *****
***** Evaluating perplexity, Epoch 0/1 *****
ppl: 1.932552456855774
Beginning of Epoch 1/1, Total Micro Batches 5116
Invalidate trace cache @ step 0: expected module 16, but got module 0
[2023-04-19 17:04:45,205] [WARNING] [stage3.py:1787:step] 1 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time
[2023-04-19 17:05:06,421] [INFO] [logging.py:96:log_dist] [Rank 0] step=10, skipped=0, lr=[0.000999962292024615], mom=[(0.9, 0.95)]
[2023-04-19 17:05:06,421] [INFO] [timer.py:199:stop] epoch=0/micro_step=20/global_step=10, RunningAvgSamplesPerSec=12.07828969080794, CurrSamplesPerSec=12.495106931233762, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:05:32,168] [INFO] [logging.py:96:log_dist] [Rank 0] step=20, skipped=0, lr=[0.0009998491737860256], mom=[(0.9, 0.95)]
[2023-04-19 17:05:32,169] [INFO] [timer.py:199:stop] epoch=0/micro_step=40/global_step=20, RunningAvgSamplesPerSec=12.27707734265837, CurrSamplesPerSec=12.316409530577367, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:05:58,637] [INFO] [logging.py:96:log_dist] [Rank 0] step=30, skipped=0, lr=[0.0009996606623460709], mom=[(0.9, 0.95)]
[2023-04-19 17:05:58,637] [INFO] [timer.py:199:stop] epoch=0/micro_step=60/global_step=30, RunningAvgSamplesPerSec=12.213891713093837, CurrSamplesPerSec=12.335717709296935, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:06:25,208] [INFO] [logging.py:96:log_dist] [Rank 0] step=40, skipped=0, lr=[0.0009993967861382895], mom=[(0.9, 0.95)]
[2023-04-19 17:06:25,208] [INFO] [timer.py:199:stop] epoch=0/micro_step=80/global_step=40, RunningAvgSamplesPerSec=12.171658146585271, CurrSamplesPerSec=12.415960783326993, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:06:50,948] [INFO] [logging.py:96:log_dist] [Rank 0] step=50, skipped=0, lr=[0.0009990575849636322], mom=[(0.9, 0.95)]
[2023-04-19 17:06:50,949] [INFO] [timer.py:199:stop] epoch=0/micro_step=100/global_step=50, RunningAvgSamplesPerSec=12.227460835941864, CurrSamplesPerSec=12.498281061505862, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:07:17,048] [INFO] [logging.py:96:log_dist] [Rank 0] step=60, skipped=0, lr=[0.0009986431099844567], mom=[(0.9, 0.95)]
[2023-04-19 17:07:17,049] [INFO] [timer.py:199:stop] epoch=0/micro_step=120/global_step=60, RunningAvgSamplesPerSec=12.235269962686647, CurrSamplesPerSec=12.427871199814515, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:07:42,760] [INFO] [logging.py:96:log_dist] [Rank 0] step=70, skipped=0, lr=[0.0009981534237168124], mom=[(0.9, 0.95)]
[2023-04-19 17:07:42,760] [INFO] [timer.py:199:stop] epoch=0/micro_step=140/global_step=70, RunningAvgSamplesPerSec=12.26760719734709, CurrSamplesPerSec=12.447521475862185, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:08:09,216] [INFO] [logging.py:96:log_dist] [Rank 0] step=80, skipped=0, lr=[0.0009975886000210103], mom=[(0.9, 0.95)]
[2023-04-19 17:08:09,216] [INFO] [timer.py:199:stop] epoch=0/micro_step=160/global_step=80, RunningAvgSamplesPerSec=12.246875617612654, CurrSamplesPerSec=12.463447132852547, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:08:34,878] [INFO] [logging.py:96:log_dist] [Rank 0] step=90, skipped=0, lr=[0.0009969487240904821], mom=[(0.9, 0.95)]
[2023-04-19 17:08:34,878] [INFO] [timer.py:199:stop] epoch=0/micro_step=180/global_step=90, RunningAvgSamplesPerSec=12.273182191155067, CurrSamplesPerSec=12.479842927239387, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:09:01,201] [INFO] [logging.py:96:log_dist] [Rank 0] step=100, skipped=0, lr=[0.0009962338924389318], mom=[(0.9, 0.95)]
[2023-04-19 17:09:01,202] [INFO] [timer.py:199:stop] epoch=0/micro_step=200/global_step=100, RunningAvgSamplesPerSec=12.262435671957197, CurrSamplesPerSec=12.444532300839375, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:09:03,712] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:09:06,241] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:09:27,458] [INFO] [logging.py:96:log_dist] [Rank 0] step=110, skipped=2, lr=[0.0009956081310737383], mom=[(0.9, 0.95)]
[2023-04-19 17:09:27,458] [INFO] [timer.py:199:stop] epoch=0/micro_step=220/global_step=110, RunningAvgSamplesPerSec=12.256601643093727, CurrSamplesPerSec=10.073982804736758, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:09:53,231] [INFO] [logging.py:96:log_dist] [Rank 0] step=120, skipped=2, lr=[0.0009947586584163801], mom=[(0.9, 0.95)]
[2023-04-19 17:09:53,232] [INFO] [timer.py:199:stop] epoch=0/micro_step=240/global_step=120, RunningAvgSamplesPerSec=12.270975908562303, CurrSamplesPerSec=12.399814784909182, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:10:19,854] [INFO] [logging.py:96:log_dist] [Rank 0] step=130, skipped=2, lr=[0.0009938345603697695], mom=[(0.9, 0.95)]
[2023-04-19 17:10:19,854] [INFO] [timer.py:199:stop] epoch=0/micro_step=260/global_step=130, RunningAvgSamplesPerSec=12.25194301856043, CurrSamplesPerSec=12.366203557310797, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:10:45,602] [INFO] [logging.py:96:log_dist] [Rank 0] step=140, skipped=2, lr=[0.0009928359763173725], mom=[(0.9, 0.95)]
[2023-04-19 17:10:45,603] [INFO] [timer.py:199:stop] epoch=0/micro_step=280/global_step=140, RunningAvgSamplesPerSec=12.26540750325886, CurrSamplesPerSec=12.465680069991771, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:11:12,054] [INFO] [logging.py:96:log_dist] [Rank 0] step=150, skipped=2, lr=[0.0009917630568775197], mom=[(0.9, 0.95)]
[2023-04-19 17:11:12,055] [INFO] [timer.py:199:stop] epoch=0/micro_step=300/global_step=150, RunningAvgSamplesPerSec=12.254730873875417, CurrSamplesPerSec=12.451094211070863, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:11:37,804] [INFO] [logging.py:96:log_dist] [Rank 0] step=160, skipped=2, lr=[0.0009906159638806912], mom=[(0.9, 0.95)]
[2023-04-19 17:11:37,805] [INFO] [timer.py:199:stop] epoch=0/micro_step=320/global_step=160, RunningAvgSamplesPerSec=12.266273586942694, CurrSamplesPerSec=12.372864453261226, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:12:04,310] [INFO] [logging.py:96:log_dist] [Rank 0] step=170, skipped=2, lr=[0.0009893948703451048], mom=[(0.9, 0.95)]
[2023-04-19 17:12:04,311] [INFO] [timer.py:199:stop] epoch=0/micro_step=340/global_step=170, RunningAvgSamplesPerSec=12.255316195957107, CurrSamplesPerSec=12.35051278684349, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:12:30,058] [INFO] [logging.py:96:log_dist] [Rank 0] step=180, skipped=2, lr=[0.00098809996045062], mom=[(0.9, 0.95)]
[2023-04-19 17:12:30,058] [INFO] [timer.py:199:stop] epoch=0/micro_step=360/global_step=180, RunningAvgSamplesPerSec=12.265586794678816, CurrSamplesPerSec=12.53894458266291, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:12:55,974] [INFO] [logging.py:96:log_dist] [Rank 0] step=190, skipped=2, lr=[0.0009867314295109592], mom=[(0.9, 0.95)]
[2023-04-19 17:12:55,974] [INFO] [timer.py:199:stop] epoch=0/micro_step=380/global_step=190, RunningAvgSamplesPerSec=12.270574293164143, CurrSamplesPerSec=12.805881607610917, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:13:21,596] [INFO] [logging.py:96:log_dist] [Rank 0] step=200, skipped=2, lr=[0.0009852894839442454], mom=[(0.9, 0.95)]
[2023-04-19 17:13:21,597] [INFO] [timer.py:199:stop] epoch=0/micro_step=400/global_step=200, RunningAvgSamplesPerSec=12.28206325598975, CurrSamplesPerSec=10.304444444615054, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:13:29,036] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:13:31,505] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:13:46,471] [INFO] [logging.py:96:log_dist] [Rank 0] step=210, skipped=4, lr=[0.0009840832147423797], mom=[(0.9, 0.95)]
[2023-04-19 17:13:46,471] [INFO] [timer.py:199:stop] epoch=0/micro_step=420/global_step=210, RunningAvgSamplesPerSec=12.309450362425165, CurrSamplesPerSec=12.82604532079847, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:14:12,095] [INFO] [logging.py:96:log_dist] [Rank 0] step=220, skipped=4, lr=[0.0009825096783456148], mom=[(0.9, 0.95)]
[2023-04-19 17:14:12,095] [INFO] [timer.py:199:stop] epoch=0/micro_step=440/global_step=220, RunningAvgSamplesPerSec=12.318099158821909, CurrSamplesPerSec=12.881070542377875, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:14:36,998] [INFO] [logging.py:96:log_dist] [Rank 0] step=230, skipped=4, lr=[0.000980863364096554], mom=[(0.9, 0.95)]
[2023-04-19 17:14:36,999] [INFO] [timer.py:199:stop] epoch=0/micro_step=460/global_step=230, RunningAvgSamplesPerSec=12.341027356371558, CurrSamplesPerSec=12.877603892322144, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:15:02,518] [INFO] [logging.py:96:log_dist] [Rank 0] step=240, skipped=4, lr=[0.0009791445203119053], mom=[(0.9, 0.95)]
[2023-04-19 17:15:02,518] [INFO] [timer.py:199:stop] epoch=0/micro_step=480/global_step=240, RunningAvgSamplesPerSec=12.349763302828249, CurrSamplesPerSec=12.845641906787987, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:15:27,392] [INFO] [logging.py:96:log_dist] [Rank 0] step=250, skipped=4, lr=[0.0009773534062481454], mom=[(0.9, 0.95)]
[2023-04-19 17:15:27,392] [INFO] [timer.py:199:stop] epoch=0/micro_step=500/global_step=250, RunningAvgSamplesPerSec=12.370237821031711, CurrSamplesPerSec=12.822156205013146, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:15:52,996] [INFO] [logging.py:96:log_dist] [Rank 0] step=260, skipped=4, lr=[0.0009754902920624147], mom=[(0.9, 0.95)]
[2023-04-19 17:15:52,996] [INFO] [timer.py:199:stop] epoch=0/micro_step=520/global_step=260, RunningAvgSamplesPerSec=12.375631075615024, CurrSamplesPerSec=12.870813186986009, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:16:17,856] [INFO] [logging.py:96:log_dist] [Rank 0] step=270, skipped=4, lr=[0.0009735554587717682], mom=[(0.9, 0.95)]
[2023-04-19 17:16:17,857] [INFO] [timer.py:199:stop] epoch=0/micro_step=540/global_step=270, RunningAvgSamplesPerSec=12.393919730920452, CurrSamplesPerSec=12.862547808911936, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:16:43,461] [INFO] [logging.py:96:log_dist] [Rank 0] step=280, skipped=4, lr=[0.0009715491982107905], mom=[(0.9, 0.95)]
[2023-04-19 17:16:43,461] [INFO] [timer.py:199:stop] epoch=0/micro_step=560/global_step=280, RunningAvgSamplesPerSec=12.398073557379359, CurrSamplesPerSec=12.863134582943513, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:17:08,936] [INFO] [logging.py:96:log_dist] [Rank 0] step=290, skipped=4, lr=[0.0009694718129875771], mom=[(0.9, 0.95)]
[2023-04-19 17:17:08,936] [INFO] [timer.py:199:stop] epoch=0/micro_step=580/global_step=290, RunningAvgSamplesPerSec=12.404108615541837, CurrSamplesPerSec=12.860413192082941, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:17:33,853] [INFO] [logging.py:96:log_dist] [Rank 0] step=300, skipped=4, lr=[0.0009673236164380912], mom=[(0.9, 0.95)]
[2023-04-19 17:17:33,853] [INFO] [timer.py:199:stop] epoch=0/micro_step=600/global_step=300, RunningAvgSamplesPerSec=12.418762449265945, CurrSamplesPerSec=12.851047499700309, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:17:46,275] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:17:48,741] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:17:59,496] [INFO] [logging.py:96:log_dist] [Rank 0] step=310, skipped=6, lr=[0.0009655542924250932], mom=[(0.9, 0.95)]
[2023-04-19 17:17:59,496] [INFO] [timer.py:199:stop] epoch=0/micro_step=620/global_step=310, RunningAvgSamplesPerSec=12.421115391503212, CurrSamplesPerSec=12.816023451561925, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:18:24,477] [INFO] [logging.py:96:log_dist] [Rank 0] step=320, skipped=6, lr=[0.0009632794591562836], mom=[(0.9, 0.95)]
[2023-04-19 17:18:24,478] [INFO] [timer.py:199:stop] epoch=0/micro_step=640/global_step=320, RunningAvgSamplesPerSec=12.433364398393774, CurrSamplesPerSec=12.829373894544624, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:18:50,281] [INFO] [logging.py:96:log_dist] [Rank 0] step=330, skipped=6, lr=[0.000960934748565705], mom=[(0.9, 0.95)]
[2023-04-19 17:18:50,281] [INFO] [timer.py:199:stop] epoch=0/micro_step=660/global_step=330, RunningAvgSamplesPerSec=12.4327725639688, CurrSamplesPerSec=12.797726234057041, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:19:15,444] [INFO] [logging.py:96:log_dist] [Rank 0] step=340, skipped=6, lr=[0.0009585205143105142], mom=[(0.9, 0.95)]
[2023-04-19 17:19:15,444] [INFO] [timer.py:199:stop] epoch=0/micro_step=680/global_step=340, RunningAvgSamplesPerSec=12.441374838659565, CurrSamplesPerSec=12.701174220816803, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:19:41,502] [INFO] [logging.py:96:log_dist] [Rank 0] step=350, skipped=6, lr=[0.0009560371205342551], mom=[(0.9, 0.95)]
[2023-04-19 17:19:41,502] [INFO] [timer.py:199:stop] epoch=0/micro_step=700/global_step=350, RunningAvgSamplesPerSec=12.437047446225632, CurrSamplesPerSec=12.582267551983822, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:20:07,018] [INFO] [logging.py:96:log_dist] [Rank 0] step=360, skipped=6, lr=[0.0009534849418119328], mom=[(0.9, 0.95)]
[2023-04-19 17:20:07,019] [INFO] [timer.py:199:stop] epoch=0/micro_step=720/global_step=360, RunningAvgSamplesPerSec=12.440282802443646, CurrSamplesPerSec=12.476507663951448, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:20:33,388] [INFO] [logging.py:96:log_dist] [Rank 0] step=370, skipped=6, lr=[0.0009508643630935172], mom=[(0.9, 0.95)]
[2023-04-19 17:20:33,388] [INFO] [timer.py:199:stop] epoch=0/micro_step=740/global_step=370, RunningAvgSamplesPerSec=12.43213407083404, CurrSamplesPerSec=12.501919098490374, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:20:59,805] [INFO] [logging.py:96:log_dist] [Rank 0] step=380, skipped=6, lr=[0.0009481757796458796], mom=[(0.9, 0.95)]
[2023-04-19 17:20:59,805] [INFO] [timer.py:199:stop] epoch=0/micro_step=760/global_step=380, RunningAvgSamplesPerSec=12.423823090381852, CurrSamplesPerSec=12.381460225246393, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:21:25,673] [INFO] [logging.py:96:log_dist] [Rank 0] step=390, skipped=6, lr=[0.0009454195969931738], mom=[(0.9, 0.95)]
[2023-04-19 17:21:25,673] [INFO] [timer.py:199:stop] epoch=0/micro_step=780/global_step=390, RunningAvgSamplesPerSec=12.422769578096686, CurrSamplesPerSec=12.376197022211878, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:21:52,290] [INFO] [logging.py:96:log_dist] [Rank 0] step=400, skipped=6, lr=[0.0009425962308556705], mom=[(0.9, 0.95)]
[2023-04-19 17:21:52,290] [INFO] [timer.py:199:stop] epoch=0/micro_step=800/global_step=400, RunningAvgSamplesPerSec=12.412703792380244, CurrSamplesPerSec=12.393729084304733, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:22:10,308] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:22:12,846] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:22:18,036] [INFO] [logging.py:96:log_dist] [Rank 0] step=410, skipped=8, lr=[0.0009402894516714383], mom=[(0.9, 0.95)]
[2023-04-19 17:22:18,036] [INFO] [timer.py:199:stop] epoch=0/micro_step=820/global_step=410, RunningAvgSamplesPerSec=12.41341628187407, CurrSamplesPerSec=12.390996757255785, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:22:44,528] [INFO] [logging.py:96:log_dist] [Rank 0] step=420, skipped=8, lr=[0.0009373462351812672], mom=[(0.9, 0.95)]
[2023-04-19 17:22:44,528] [INFO] [timer.py:199:stop] epoch=0/micro_step=840/global_step=420, RunningAvgSamplesPerSec=12.405510418676558, CurrSamplesPerSec=12.443687744002439, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:23:10,274] [INFO] [logging.py:96:log_dist] [Rank 0] step=430, skipped=8, lr=[0.0009343370529268123], mom=[(0.9, 0.95)]
[2023-04-19 17:23:10,274] [INFO] [timer.py:199:stop] epoch=0/micro_step=860/global_step=430, RunningAvgSamplesPerSec=12.406355781250136, CurrSamplesPerSec=12.453858887280555, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:23:36,828] [INFO] [logging.py:96:log_dist] [Rank 0] step=440, skipped=8, lr=[0.000931262358788755], mom=[(0.9, 0.95)]
[2023-04-19 17:23:36,829] [INFO] [timer.py:199:stop] epoch=0/micro_step=880/global_step=440, RunningAvgSamplesPerSec=12.398296176552364, CurrSamplesPerSec=12.41375136191017, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:24:03,063] [INFO] [logging.py:96:log_dist] [Rank 0] step=450, skipped=8, lr=[0.000928122616529059], mom=[(0.9, 0.95)]
[2023-04-19 17:24:03,064] [INFO] [timer.py:199:stop] epoch=0/micro_step=900/global_step=450, RunningAvgSamplesPerSec=12.394027658246998, CurrSamplesPerSec=10.898765305383344, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:24:29,250] [INFO] [logging.py:96:log_dist] [Rank 0] step=460, skipped=8, lr=[0.0009249182997210198], mom=[(0.9, 0.95)]
[2023-04-19 17:24:29,250] [INFO] [timer.py:199:stop] epoch=0/micro_step=920/global_step=460, RunningAvgSamplesPerSec=12.390452563746633, CurrSamplesPerSec=12.425945131237496, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:24:55,622] [INFO] [logging.py:96:log_dist] [Rank 0] step=470, skipped=8, lr=[0.0009216498916778344], mom=[(0.9, 0.95)]
[2023-04-19 17:24:55,623] [INFO] [timer.py:199:stop] epoch=0/micro_step=940/global_step=470, RunningAvgSamplesPerSec=12.38512612561435, CurrSamplesPerSec=12.463959862063918, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:25:21,314] [INFO] [logging.py:96:log_dist] [Rank 0] step=480, skipped=8, lr=[0.0009183178853797029], mom=[(0.9, 0.95)]
[2023-04-19 17:25:21,314] [INFO] [timer.py:199:stop] epoch=0/micro_step=960/global_step=480, RunningAvgSamplesPerSec=12.386858313326691, CurrSamplesPerSec=12.438629725788537, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:25:47,838] [INFO] [logging.py:96:log_dist] [Rank 0] step=490, skipped=8, lr=[0.0009149227833994717], mom=[(0.9, 0.95)]
[2023-04-19 17:25:47,838] [INFO] [timer.py:199:stop] epoch=0/micro_step=980/global_step=490, RunningAvgSamplesPerSec=12.38034147155676, CurrSamplesPerSec=12.433708277773485, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:26:13,689] [INFO] [logging.py:96:log_dist] [Rank 0] step=500, skipped=8, lr=[0.000911465097826828], mom=[(0.9, 0.95)]
[2023-04-19 17:26:13,690] [INFO] [timer.py:199:stop] epoch=0/micro_step=1000/global_step=500, RunningAvgSamplesPerSec=12.380554445613633, CurrSamplesPerSec=12.456449068622906, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:26:37,501] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:26:40,028] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:26:40,028] [INFO] [logging.py:96:log_dist] [Rank 0] step=510, skipped=10, lr=[0.0009086542393346895], mom=[(0.9, 0.95)]
[2023-04-19 17:26:40,029] [INFO] [timer.py:199:stop] epoch=0/micro_step=1020/global_step=510, RunningAvgSamplesPerSec=12.376163880112658, CurrSamplesPerSec=12.67544033782103, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:27:05,740] [INFO] [logging.py:96:log_dist] [Rank 0] step=520, skipped=10, lr=[0.0009050852238427441], mom=[(0.9, 0.95)]
[2023-04-19 17:27:05,741] [INFO] [timer.py:199:stop] epoch=0/micro_step=1040/global_step=520, RunningAvgSamplesPerSec=12.377737660987972, CurrSamplesPerSec=12.420433708306238, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:27:32,180] [INFO] [logging.py:96:log_dist] [Rank 0] step=530, skipped=10, lr=[0.0009014551085762004], mom=[(0.9, 0.95)]
[2023-04-19 17:27:32,180] [INFO] [timer.py:199:stop] epoch=0/micro_step=1060/global_step=530, RunningAvgSamplesPerSec=12.372661889023702, CurrSamplesPerSec=12.377309799385882, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:27:58,847] [INFO] [logging.py:96:log_dist] [Rank 0] step=540, skipped=10, lr=[0.0008977644410722474], mom=[(0.9, 0.95)]
[2023-04-19 17:27:58,848] [INFO] [timer.py:199:stop] epoch=0/micro_step=1080/global_step=540, RunningAvgSamplesPerSec=12.3657484083089, CurrSamplesPerSec=10.83456878461236, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:28:24,615] [INFO] [logging.py:96:log_dist] [Rank 0] step=550, skipped=10, lr=[0.0008940137780012825], mom=[(0.9, 0.95)]
[2023-04-19 17:28:24,615] [INFO] [timer.py:199:stop] epoch=0/micro_step=1100/global_step=550, RunningAvgSamplesPerSec=12.366938514326245, CurrSamplesPerSec=12.479740812725497, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:28:50,954] [INFO] [logging.py:96:log_dist] [Rank 0] step=560, skipped=10, lr=[0.0008902036850829485], mom=[(0.9, 0.95)]
[2023-04-19 17:28:50,954] [INFO] [timer.py:199:stop] epoch=0/micro_step=1120/global_step=560, RunningAvgSamplesPerSec=12.363198818138457, CurrSamplesPerSec=12.443068244459347, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:29:16,787] [INFO] [logging.py:96:log_dist] [Rank 0] step=570, skipped=10, lr=[0.0008863347370008057], mom=[(0.9, 0.95)]
[2023-04-19 17:29:16,787] [INFO] [timer.py:199:stop] epoch=0/micro_step=1140/global_step=570, RunningAvgSamplesPerSec=12.3638415350952, CurrSamplesPerSec=12.362678227713483, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:29:43,335] [INFO] [logging.py:96:log_dist] [Rank 0] step=580, skipped=10, lr=[0.0008824075173156499], mom=[(0.9, 0.95)]
[2023-04-19 17:29:43,336] [INFO] [timer.py:199:stop] epoch=0/micro_step=1160/global_step=580, RunningAvgSamplesPerSec=12.35855420493839, CurrSamplesPerSec=12.404735802011816, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:30:09,222] [INFO] [logging.py:96:log_dist] [Rank 0] step=590, skipped=10, lr=[0.0008784226183774943], mom=[(0.9, 0.95)]
[2023-04-19 17:30:09,222] [INFO] [timer.py:199:stop] epoch=0/micro_step=1180/global_step=590, RunningAvgSamplesPerSec=12.358818701228529, CurrSamplesPerSec=12.365673775252885, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:30:35,854] [INFO] [logging.py:96:log_dist] [Rank 0] step=600, skipped=10, lr=[0.000874380641236223], mom=[(0.9, 0.95)]
[2023-04-19 17:30:35,854] [INFO] [timer.py:199:stop] epoch=0/micro_step=1200/global_step=600, RunningAvgSamplesPerSec=12.353132909214159, CurrSamplesPerSec=12.35099239814929, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:31:01,682] [INFO] [logging.py:96:log_dist] [Rank 0] step=610, skipped=10, lr=[0.0008702821955509344], mom=[(0.9, 0.95)]
[2023-04-19 17:31:01,682] [INFO] [timer.py:199:stop] epoch=0/micro_step=1220/global_step=610, RunningAvgSamplesPerSec=12.353940832433471, CurrSamplesPerSec=12.39328276766209, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:31:04,560] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:31:07,486] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:31:28,208] [INFO] [logging.py:96:log_dist] [Rank 0] step=620, skipped=12, lr=[0.0008669631967817167], mom=[(0.9, 0.95)]
[2023-04-19 17:31:28,208] [INFO] [timer.py:199:stop] epoch=0/micro_step=1240/global_step=620, RunningAvgSamplesPerSec=12.349334304280147, CurrSamplesPerSec=12.38552657235039, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:31:54,781] [INFO] [logging.py:96:log_dist] [Rank 0] step=630, skipped=12, lr=[0.0008627646711857188], mom=[(0.9, 0.95)]
[2023-04-19 17:31:54,782] [INFO] [timer.py:199:stop] epoch=0/micro_step=1260/global_step=630, RunningAvgSamplesPerSec=12.344519090997533, CurrSamplesPerSec=10.799963854672287, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:32:20,670] [INFO] [logging.py:96:log_dist] [Rank 0] step=640, skipped=12, lr=[0.0008585114291045544], mom=[(0.9, 0.95)]
[2023-04-19 17:32:20,671] [INFO] [timer.py:199:stop] epoch=0/micro_step=1280/global_step=640, RunningAvgSamplesPerSec=12.344965329862202, CurrSamplesPerSec=12.400174503397956, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:32:47,133] [INFO] [logging.py:96:log_dist] [Rank 0] step=650, skipped=12, lr=[0.0008542041120628143], mom=[(0.9, 0.95)]
[2023-04-19 17:32:47,133] [INFO] [timer.py:199:stop] epoch=0/micro_step=1300/global_step=650, RunningAvgSamplesPerSec=12.341185303447821, CurrSamplesPerSec=12.410061177588837, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:33:13,000] [INFO] [logging.py:96:log_dist] [Rank 0] step=660, skipped=12, lr=[0.0008498433697413186], mom=[(0.9, 0.95)]
[2023-04-19 17:33:13,001] [INFO] [timer.py:199:stop] epoch=0/micro_step=1320/global_step=660, RunningAvgSamplesPerSec=12.341826339333801, CurrSamplesPerSec=12.325113758079137, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:33:39,578] [INFO] [logging.py:96:log_dist] [Rank 0] step=670, skipped=12, lr=[0.0008454298598791235], mom=[(0.9, 0.95)]
[2023-04-19 17:33:39,579] [INFO] [timer.py:199:stop] epoch=0/micro_step=1340/global_step=670, RunningAvgSamplesPerSec=12.337384792748615, CurrSamplesPerSec=12.432642918761928, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:34:05,425] [INFO] [logging.py:96:log_dist] [Rank 0] step=680, skipped=12, lr=[0.000840964248174314], mom=[(0.9, 0.95)]
[2023-04-19 17:34:05,426] [INFO] [timer.py:199:stop] epoch=0/micro_step=1360/global_step=680, RunningAvgSamplesPerSec=12.338203936574846, CurrSamplesPerSec=12.39753896095559, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:34:32,004] [INFO] [logging.py:96:log_dist] [Rank 0] step=690, skipped=12, lr=[0.0008364472081835954], mom=[(0.9, 0.95)]
[2023-04-19 17:34:32,004] [INFO] [timer.py:199:stop] epoch=0/micro_step=1380/global_step=690, RunningAvgSamplesPerSec=12.333943151295635, CurrSamplesPerSec=12.388178734300265, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:34:58,287] [INFO] [logging.py:96:log_dist] [Rank 0] step=700, skipped=12, lr=[0.0008318794212206986], mom=[(0.9, 0.95)]
[2023-04-19 17:34:58,288] [INFO] [timer.py:199:stop] epoch=0/micro_step=1400/global_step=700, RunningAvgSamplesPerSec=12.331818651748383, CurrSamplesPerSec=10.815059116797121, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:35:24,531] [INFO] [logging.py:96:log_dist] [Rank 0] step=710, skipped=12, lr=[0.0008272615762536171], mom=[(0.9, 0.95)]
[2023-04-19 17:35:24,532] [INFO] [timer.py:199:stop] epoch=0/micro_step=1420/global_step=710, RunningAvgSamplesPerSec=12.330020191929695, CurrSamplesPerSec=12.390247522970165, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:35:32,232] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:35:34,771] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:35:50,892] [INFO] [logging.py:96:log_dist] [Rank 0] step=720, skipped=14, lr=[0.0008235317263262469], mom=[(0.9, 0.95)]
[2023-04-19 17:35:50,892] [INFO] [timer.py:199:stop] epoch=0/micro_step=1440/global_step=720, RunningAvgSamplesPerSec=12.327496611969542, CurrSamplesPerSec=12.364812549050821, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:36:16,725] [INFO] [logging.py:96:log_dist] [Rank 0] step=730, skipped=14, lr=[0.0008188255371846346], mom=[(0.9, 0.95)]
[2023-04-19 17:36:16,725] [INFO] [timer.py:199:stop] epoch=0/micro_step=1460/global_step=730, RunningAvgSamplesPerSec=12.328485193644248, CurrSamplesPerSec=12.39404266958273, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:36:43,182] [INFO] [logging.py:96:log_dist] [Rank 0] step=740, skipped=14, lr=[0.0008140712589809891], mom=[(0.9, 0.95)]
[2023-04-19 17:36:43,182] [INFO] [timer.py:199:stop] epoch=0/micro_step=1480/global_step=740, RunningAvgSamplesPerSec=12.32543440337834, CurrSamplesPerSec=12.378232129443344, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:37:09,039] [INFO] [logging.py:96:log_dist] [Rank 0] step=750, skipped=14, lr=[0.0008092696088121323], mom=[(0.9, 0.95)]
[2023-04-19 17:37:09,039] [INFO] [timer.py:199:stop] epoch=0/micro_step=1500/global_step=750, RunningAvgSamplesPerSec=12.326270629881153, CurrSamplesPerSec=12.410741659317063, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:37:35,654] [INFO] [logging.py:96:log_dist] [Rank 0] step=760, skipped=14, lr=[0.0008044213109200901], mom=[(0.9, 0.95)]
[2023-04-19 17:37:35,655] [INFO] [timer.py:199:stop] epoch=0/micro_step=1520/global_step=760, RunningAvgSamplesPerSec=12.322338561705967, CurrSamplesPerSec=12.403199713747565, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:38:01,485] [INFO] [logging.py:96:log_dist] [Rank 0] step=770, skipped=14, lr=[0.0007995270965828522], mom=[(0.9, 0.95)]
[2023-04-19 17:38:01,486] [INFO] [timer.py:199:stop] epoch=0/micro_step=1540/global_step=770, RunningAvgSamplesPerSec=12.32335401862153, CurrSamplesPerSec=12.418311166214071, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:38:27,898] [INFO] [logging.py:96:log_dist] [Rank 0] step=780, skipped=14, lr=[0.0007945877040040741], mom=[(0.9, 0.95)]
[2023-04-19 17:38:27,899] [INFO] [timer.py:199:stop] epoch=0/micro_step=1560/global_step=780, RunningAvgSamplesPerSec=12.320793923911, CurrSamplesPerSec=12.407547599586076, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:38:54,088] [INFO] [logging.py:96:log_dist] [Rank 0] step=790, skipped=14, lr=[0.0007896038782017308], mom=[(0.9, 0.95)]
[2023-04-19 17:38:54,089] [INFO] [timer.py:199:stop] epoch=0/micro_step=1580/global_step=790, RunningAvgSamplesPerSec=12.319644966599517, CurrSamplesPerSec=12.290209522225812, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:39:19,990] [INFO] [logging.py:96:log_dist] [Rank 0] step=800, skipped=14, lr=[0.0007845763708957448], mom=[(0.9, 0.95)]
[2023-04-19 17:39:19,990] [INFO] [timer.py:199:stop] epoch=0/micro_step=1600/global_step=800, RunningAvgSamplesPerSec=12.320236636211249, CurrSamplesPerSec=12.744466835576597, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:39:45,824] [INFO] [logging.py:96:log_dist] [Rank 0] step=810, skipped=14, lr=[0.0007795059403946033], mom=[(0.9, 0.95)]
[2023-04-19 17:39:45,825] [INFO] [timer.py:199:stop] epoch=0/micro_step=1620/global_step=810, RunningAvgSamplesPerSec=12.321208267862733, CurrSamplesPerSec=12.790884182215338, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:39:58,273] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:40:00,745] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:40:10,738] [INFO] [logging.py:96:log_dist] [Rank 0] step=820, skipped=16, lr=[0.0007754192050125431], mom=[(0.9, 0.95)]
[2023-04-19 17:40:10,738] [INFO] [timer.py:199:stop] epoch=0/micro_step=1640/global_step=820, RunningAvgSamplesPerSec=12.327498662124329, CurrSamplesPerSec=12.849750726700075, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:40:36,307] [INFO] [logging.py:96:log_dist] [Rank 0] step=830, skipped=16, lr=[0.000770273444289497], mom=[(0.9, 0.95)]
[2023-04-19 17:40:36,307] [INFO] [timer.py:199:stop] epoch=0/micro_step=1660/global_step=830, RunningAvgSamplesPerSec=12.329883167590443, CurrSamplesPerSec=12.826796704158907, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:41:01,233] [INFO] [logging.py:96:log_dist] [Rank 0] step=840, skipped=16, lr=[0.0007650869177089128], mom=[(0.9, 0.95)]
[2023-04-19 17:41:01,234] [INFO] [timer.py:199:stop] epoch=0/micro_step=1680/global_step=840, RunningAvgSamplesPerSec=12.335855108865013, CurrSamplesPerSec=12.83786436378276, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:41:26,908] [INFO] [logging.py:96:log_dist] [Rank 0] step=850, skipped=16, lr=[0.0007598604075644574], mom=[(0.9, 0.95)]
[2023-04-19 17:41:26,909] [INFO] [timer.py:199:stop] epoch=0/micro_step=1700/global_step=850, RunningAvgSamplesPerSec=12.337496481370808, CurrSamplesPerSec=12.849296794964276, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:41:51,839] [INFO] [logging.py:96:log_dist] [Rank 0] step=860, skipped=16, lr=[0.0007545947021805939], mom=[(0.9, 0.95)]
[2023-04-19 17:41:51,839] [INFO] [timer.py:199:stop] epoch=0/micro_step=1720/global_step=860, RunningAvgSamplesPerSec=12.343223968422315, CurrSamplesPerSec=12.837561070790468, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:42:17,574] [INFO] [logging.py:96:log_dist] [Rank 0] step=870, skipped=16, lr=[0.0007492905957936784], mom=[(0.9, 0.95)]
[2023-04-19 17:42:17,575] [INFO] [timer.py:199:stop] epoch=0/micro_step=1740/global_step=870, RunningAvgSamplesPerSec=12.344409548735772, CurrSamplesPerSec=12.804170059275858, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:42:43,355] [INFO] [logging.py:96:log_dist] [Rank 0] step=880, skipped=16, lr=[0.0007439488884321635], mom=[(0.9, 0.95)]
[2023-04-19 17:42:43,355] [INFO] [timer.py:199:stop] epoch=0/micro_step=1760/global_step=880, RunningAvgSamplesPerSec=12.345321702239133, CurrSamplesPerSec=11.084045608043938, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:43:08,447] [INFO] [logging.py:96:log_dist] [Rank 0] step=890, skipped=16, lr=[0.0007385703857959276], mom=[(0.9, 0.95)]
[2023-04-19 17:43:08,447] [INFO] [timer.py:199:stop] epoch=0/micro_step=1780/global_step=890, RunningAvgSamplesPerSec=12.349907530652988, CurrSamplesPerSec=12.766375184074995, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:43:34,362] [INFO] [logging.py:96:log_dist] [Rank 0] step=900, skipped=16, lr=[0.0007331558991347511], mom=[(0.9, 0.95)]
[2023-04-19 17:43:34,363] [INFO] [timer.py:199:stop] epoch=0/micro_step=1800/global_step=900, RunningAvgSamplesPerSec=12.350024217868127, CurrSamplesPerSec=12.711335014884598, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:43:59,715] [INFO] [logging.py:96:log_dist] [Rank 0] step=910, skipped=16, lr=[0.0007277062451259528], mom=[(0.9, 0.95)]
[2023-04-19 17:43:59,716] [INFO] [timer.py:199:stop] epoch=0/micro_step=1820/global_step=910, RunningAvgSamplesPerSec=12.353091868169075, CurrSamplesPerSec=12.581144742324476, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:44:18,143] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:44:20,668] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:44:25,811] [INFO] [logging.py:96:log_dist] [Rank 0] step=920, skipped=18, lr=[0.0007233217536252489], mom=[(0.9, 0.95)]
[2023-04-19 17:44:25,811] [INFO] [timer.py:199:stop] epoch=0/micro_step=1840/global_step=920, RunningAvgSamplesPerSec=12.35223511923478, CurrSamplesPerSec=12.48053108339018, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:44:51,480] [INFO] [logging.py:96:log_dist] [Rank 0] step=930, skipped=18, lr=[0.0007178108732699562], mom=[(0.9, 0.95)]
[2023-04-19 17:44:51,480] [INFO] [timer.py:199:stop] epoch=0/micro_step=1860/global_step=930, RunningAvgSamplesPerSec=12.3535888911587, CurrSamplesPerSec=12.434895936355083, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:45:18,016] [INFO] [logging.py:96:log_dist] [Rank 0] step=940, skipped=18, lr=[0.000712267140086472], mom=[(0.9, 0.95)]
[2023-04-19 17:45:18,016] [INFO] [timer.py:199:stop] epoch=0/micro_step=1880/global_step=940, RunningAvgSamplesPerSec=12.350506541077507, CurrSamplesPerSec=12.352032441613526, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:45:44,301] [INFO] [logging.py:96:log_dist] [Rank 0] step=950, skipped=18, lr=[0.0007066913902466141], mom=[(0.9, 0.95)]
[2023-04-19 17:45:44,301] [INFO] [timer.py:199:stop] epoch=0/micro_step=1900/global_step=950, RunningAvgSamplesPerSec=12.34875418553038, CurrSamplesPerSec=10.873309381187074, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:46:10,498] [INFO] [logging.py:96:log_dist] [Rank 0] step=960, skipped=18, lr=[0.0007010844647513335], mom=[(0.9, 0.95)]
[2023-04-19 17:46:10,499] [INFO] [timer.py:199:stop] epoch=0/micro_step=1920/global_step=960, RunningAvgSamplesPerSec=12.347471208831822, CurrSamplesPerSec=12.461529691197287, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:46:37,017] [INFO] [logging.py:96:log_dist] [Rank 0] step=970, skipped=18, lr=[0.000695447209303864], mom=[(0.9, 0.95)]
[2023-04-19 17:46:37,018] [INFO] [timer.py:199:stop] epoch=0/micro_step=1940/global_step=970, RunningAvgSamplesPerSec=12.344635758493899, CurrSamplesPerSec=10.841980905932228, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:47:02,810] [INFO] [logging.py:96:log_dist] [Rank 0] step=980, skipped=18, lr=[0.0006897804741821649], mom=[(0.9, 0.95)]
[2023-04-19 17:47:02,810] [INFO] [timer.py:199:stop] epoch=0/micro_step=1960/global_step=980, RunningAvgSamplesPerSec=12.345394722587116, CurrSamplesPerSec=12.393337697206483, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:47:29,294] [INFO] [logging.py:96:log_dist] [Rank 0] step=990, skipped=18, lr=[0.0006840851141106694], mom=[(0.9, 0.95)]
[2023-04-19 17:47:29,294] [INFO] [timer.py:199:stop] epoch=0/micro_step=1980/global_step=990, RunningAvgSamplesPerSec=12.34280801200078, CurrSamplesPerSec=12.368272990522472, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:47:55,162] [INFO] [logging.py:96:log_dist] [Rank 0] step=1000, skipped=18, lr=[0.0006783619881313676], mom=[(0.9, 0.95)]
[2023-04-19 17:47:55,162] [INFO] [timer.py:199:stop] epoch=0/micro_step=2000/global_step=1000, RunningAvgSamplesPerSec=12.343210472186934, CurrSamplesPerSec=12.339334311891653, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:48:21,596] [INFO] [logging.py:96:log_dist] [Rank 0] step=1010, skipped=18, lr=[0.0006726119594742333], mom=[(0.9, 0.95)]
[2023-04-19 17:48:21,597] [INFO] [timer.py:199:stop] epoch=0/micro_step=2020/global_step=1010, RunningAvgSamplesPerSec=12.340929143415744, CurrSamplesPerSec=12.375618457152315, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:48:44,790] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:48:47,330] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:48:47,331] [INFO] [logging.py:96:log_dist] [Rank 0] step=1020, skipped=20, lr=[0.0006679931493048548], mom=[(0.9, 0.95)]
[2023-04-19 17:48:47,331] [INFO] [timer.py:199:stop] epoch=0/micro_step=2040/global_step=1020, RunningAvgSamplesPerSec=12.341967169670106, CurrSamplesPerSec=12.609502682829376, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:49:13,879] [INFO] [logging.py:96:log_dist] [Rank 0] step=1030, skipped=20, lr=[0.000662196884036101], mom=[(0.9, 0.95)]
[2023-04-19 17:49:13,880] [INFO] [timer.py:199:stop] epoch=0/micro_step=2060/global_step=1030, RunningAvgSamplesPerSec=12.339214394571659, CurrSamplesPerSec=12.447448749159538, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:49:40,041] [INFO] [logging.py:96:log_dist] [Rank 0] step=1040, skipped=20, lr=[0.0006563761543029039], mom=[(0.9, 0.95)]
[2023-04-19 17:49:40,042] [INFO] [timer.py:199:stop] epoch=0/micro_step=2080/global_step=1040, RunningAvgSamplesPerSec=12.338287948072862, CurrSamplesPerSec=10.883461229547047, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:50:06,208] [INFO] [logging.py:96:log_dist] [Rank 0] step=1050, skipped=20, lr=[0.000650531838056998], mom=[(0.9, 0.95)]
[2023-04-19 17:50:06,208] [INFO] [timer.py:199:stop] epoch=0/micro_step=2100/global_step=1050, RunningAvgSamplesPerSec=12.337358766530718, CurrSamplesPerSec=12.446037095975667, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:50:32,591] [INFO] [logging.py:96:log_dist] [Rank 0] step=1060, skipped=20, lr=[0.0006446648168077156], mom=[(0.9, 0.95)]
[2023-04-19 17:50:32,592] [INFO] [timer.py:199:stop] epoch=0/micro_step=2120/global_step=1060, RunningAvgSamplesPerSec=12.335472446032648, CurrSamplesPerSec=12.43088691461683, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:50:58,360] [INFO] [logging.py:96:log_dist] [Rank 0] step=1070, skipped=20, lr=[0.000638775975489028], mom=[(0.9, 0.95)]
[2023-04-19 17:50:58,361] [INFO] [timer.py:199:stop] epoch=0/micro_step=2140/global_step=1070, RunningAvgSamplesPerSec=12.336356910225373, CurrSamplesPerSec=12.431173598785648, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:51:24,880] [INFO] [logging.py:96:log_dist] [Rank 0] step=1080, skipped=20, lr=[0.0006328662023260695], mom=[(0.9, 0.95)]
[2023-04-19 17:51:24,880] [INFO] [timer.py:199:stop] epoch=0/micro_step=2160/global_step=1080, RunningAvgSamplesPerSec=12.333914084704624, CurrSamplesPerSec=12.393311376739035, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:51:50,708] [INFO] [logging.py:96:log_dist] [Rank 0] step=1090, skipped=20, lr=[0.0006269363887011636], mom=[(0.9, 0.95)]
[2023-04-19 17:51:50,709] [INFO] [timer.py:199:stop] epoch=0/micro_step=2180/global_step=1090, RunningAvgSamplesPerSec=12.334540626156128, CurrSamplesPerSec=12.313492024901896, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:52:17,372] [INFO] [logging.py:96:log_dist] [Rank 0] step=1100, skipped=20, lr=[0.0006209874290193754], mom=[(0.9, 0.95)]
[2023-04-19 17:52:17,372] [INFO] [timer.py:199:stop] epoch=0/micro_step=2200/global_step=1100, RunningAvgSamplesPerSec=12.33154887382222, CurrSamplesPerSec=12.279735312421261, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:52:43,396] [INFO] [logging.py:96:log_dist] [Rank 0] step=1110, skipped=20, lr=[0.0006150202205736057], mom=[(0.9, 0.95)]
[2023-04-19 17:52:43,397] [INFO] [timer.py:199:stop] epoch=0/micro_step=2220/global_step=1110, RunningAvgSamplesPerSec=12.331350008579633, CurrSamplesPerSec=12.308929838645925, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:53:10,046] [INFO] [logging.py:96:log_dist] [Rank 0] step=1120, skipped=20, lr=[0.0006090356634092513], mom=[(0.9, 0.95)]
[2023-04-19 17:53:10,047] [INFO] [timer.py:199:stop] epoch=0/micro_step=2240/global_step=1120, RunningAvgSamplesPerSec=12.328499180436237, CurrSamplesPerSec=12.302516879811852, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:53:12,580] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:53:15,130] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:53:36,361] [INFO] [logging.py:96:log_dist] [Rank 0] step=1130, skipped=22, lr=[0.0006042361331048955], mom=[(0.9, 0.95)]
[2023-04-19 17:53:36,361] [INFO] [timer.py:199:stop] epoch=0/micro_step=2260/global_step=1130, RunningAvgSamplesPerSec=12.327112608764459, CurrSamplesPerSec=12.31348072818655, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:54:02,770] [INFO] [logging.py:96:log_dist] [Rank 0] step=1140, skipped=22, lr=[0.0005982226246272145], mom=[(0.9, 0.95)]
[2023-04-19 17:54:02,771] [INFO] [timer.py:199:stop] epoch=0/micro_step=2280/global_step=1140, RunningAvgSamplesPerSec=12.3253524395009, CurrSamplesPerSec=12.32361769217392, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:54:29,536] [INFO] [logging.py:96:log_dist] [Rank 0] step=1150, skipped=22, lr=[0.0005921943010442869], mom=[(0.9, 0.95)]
[2023-04-19 17:54:29,537] [INFO] [timer.py:199:stop] epoch=0/micro_step=2300/global_step=1150, RunningAvgSamplesPerSec=12.322150881860248, CurrSamplesPerSec=12.302494326659394, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:54:55,579] [INFO] [logging.py:96:log_dist] [Rank 0] step=1160, skipped=22, lr=[0.0005861520716196217], mom=[(0.9, 0.95)]
[2023-04-19 17:54:55,579] [INFO] [timer.py:199:stop] epoch=0/micro_step=2320/global_step=1160, RunningAvgSamplesPerSec=12.321969112440607, CurrSamplesPerSec=12.287758879731456, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:55:22,343] [INFO] [logging.py:96:log_dist] [Rank 0] step=1170, skipped=22, lr=[0.0005800968477141724], mom=[(0.9, 0.95)]
[2023-04-19 17:55:22,344] [INFO] [timer.py:199:stop] epoch=0/micro_step=2340/global_step=1170, RunningAvgSamplesPerSec=12.318860355457225, CurrSamplesPerSec=12.258176434330014, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:55:48,361] [INFO] [logging.py:96:log_dist] [Rank 0] step=1180, skipped=22, lr=[0.000574029542648875], mom=[(0.9, 0.95)]
[2023-04-19 17:55:48,361] [INFO] [timer.py:199:stop] epoch=0/micro_step=2360/global_step=1180, RunningAvgSamplesPerSec=12.318809050479222, CurrSamplesPerSec=12.348782177117398, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:56:14,938] [INFO] [logging.py:96:log_dist] [Rank 0] step=1190, skipped=22, lr=[0.0005679510715668897], mom=[(0.9, 0.95)]
[2023-04-19 17:56:14,939] [INFO] [timer.py:199:stop] epoch=0/micro_step=2380/global_step=1190, RunningAvgSamplesPerSec=12.316525641512154, CurrSamplesPerSec=12.347010026434933, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:56:41,307] [INFO] [logging.py:96:log_dist] [Rank 0] step=1200, skipped=22, lr=[0.0005618623512955685], mom=[(0.9, 0.95)]
[2023-04-19 17:56:41,308] [INFO] [timer.py:199:stop] epoch=0/micro_step=2400/global_step=1200, RunningAvgSamplesPerSec=12.315105038960837, CurrSamplesPerSec=10.827393883169135, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:57:07,704] [INFO] [logging.py:96:log_dist] [Rank 0] step=1210, skipped=22, lr=[0.0005557643002081674], mom=[(0.9, 0.95)]
[2023-04-19 17:57:07,705] [INFO] [timer.py:199:stop] epoch=0/micro_step=2420/global_step=1210, RunningAvgSamplesPerSec=12.313597870894732, CurrSamplesPerSec=12.29607905829239, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:57:34,436] [INFO] [logging.py:96:log_dist] [Rank 0] step=1220, skipped=22, lr=[0.000549657838085328], mom=[(0.9, 0.95)]
[2023-04-19 17:57:34,437] [INFO] [timer.py:199:stop] epoch=0/micro_step=2440/global_step=1220, RunningAvgSamplesPerSec=12.3108149927377, CurrSamplesPerSec=10.727947607851789, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:57:42,160] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 17:57:44,721] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 17:58:00,350] [INFO] [logging.py:96:log_dist] [Rank 0] step=1230, skipped=24, lr=[0.000544767231347586], mom=[(0.9, 0.95)]
[2023-04-19 17:58:00,351] [INFO] [timer.py:199:stop] epoch=0/micro_step=2460/global_step=1230, RunningAvgSamplesPerSec=12.311230504672189, CurrSamplesPerSec=12.343848682564769, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:58:27,105] [INFO] [logging.py:96:log_dist] [Rank 0] step=1240, skipped=24, lr=[0.0005386479511690275], mom=[(0.9, 0.95)]
[2023-04-19 17:58:27,106] [INFO] [timer.py:199:stop] epoch=0/micro_step=2480/global_step=1240, RunningAvgSamplesPerSec=12.3084254813281, CurrSamplesPerSec=12.358059046593949, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:58:53,096] [INFO] [logging.py:96:log_dist] [Rank 0] step=1250, skipped=24, lr=[0.0005325228416465036], mom=[(0.9, 0.95)]
[2023-04-19 17:58:53,096] [INFO] [timer.py:199:stop] epoch=0/micro_step=2500/global_step=1250, RunningAvgSamplesPerSec=12.308565558430116, CurrSamplesPerSec=12.362821707537037, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:59:19,726] [INFO] [logging.py:96:log_dist] [Rank 0] step=1260, skipped=24, lr=[0.0005263928266419306], mom=[(0.9, 0.95)]
[2023-04-19 17:59:19,726] [INFO] [timer.py:199:stop] epoch=0/micro_step=2520/global_step=1260, RunningAvgSamplesPerSec=12.306294872236686, CurrSamplesPerSec=12.285429537813988, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 17:59:45,724] [INFO] [logging.py:96:log_dist] [Rank 0] step=1270, skipped=24, lr=[0.0005202588307571282], mom=[(0.9, 0.95)]
[2023-04-19 17:59:45,725] [INFO] [timer.py:199:stop] epoch=0/micro_step=2540/global_step=1270, RunningAvgSamplesPerSec=12.306418820802854, CurrSamplesPerSec=12.375375407494394, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 18:00:12,349] [INFO] [logging.py:96:log_dist] [Rank 0] step=1280, skipped=24, lr=[0.0005141217791943596], mom=[(0.9, 0.95)]
[2023-04-19 18:00:12,350] [INFO] [timer.py:199:stop] epoch=0/micro_step=2560/global_step=1280, RunningAvgSamplesPerSec=12.304221787202156, CurrSamplesPerSec=12.32757139885218, MemAllocated=1.95GB, MaxMemAllocated=13.61GB
[2023-04-19 18:00:38,706] [INFO] [logging.py:96:log_dist] [Rank 0] step=1290, skipped=24, lr=[0.0005079825976167822], mom=[(0.9, 0.95)]
[2023-04-19 18:00:38,707] [INFO] [timer.py:199:stop] epoch=0/micro_step=2580/global_step=1290, RunningAvgSamplesPerSec=12.303041637793852, CurrSamplesPerSec=10.799450282422233, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:01:05,115] [INFO] [logging.py:96:log_dist] [Rank 0] step=1300, skipped=24, lr=[0.000501842212008827], mom=[(0.9, 0.95)]
[2023-04-19 18:01:05,116] [INFO] [timer.py:199:stop] epoch=0/micro_step=2600/global_step=1300, RunningAvgSamplesPerSec=12.301692628837143, CurrSamplesPerSec=12.321747554864698, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:01:31,885] [INFO] [logging.py:96:log_dist] [Rank 0] step=1310, skipped=24, lr=[0.0004957015485365313], mom=[(0.9, 0.95)]
[2023-04-19 18:01:31,886] [INFO] [timer.py:199:stop] epoch=0/micro_step=2620/global_step=1310, RunningAvgSamplesPerSec=12.299057767730432, CurrSamplesPerSec=10.716507333570151, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:01:57,912] [INFO] [logging.py:96:log_dist] [Rank 0] step=1320, skipped=24, lr=[0.0004895615334078436], mom=[(0.9, 0.95)]
[2023-04-19 18:01:57,913] [INFO] [timer.py:199:stop] epoch=0/micro_step=2640/global_step=1320, RunningAvgSamplesPerSec=12.299131376088003, CurrSamplesPerSec=12.290784630892936, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:02:11,118] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:02:13,676] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:02:24,488] [INFO] [logging.py:96:log_dist] [Rank 0] step=1330, skipped=26, lr=[0.0004846506104651698], mom=[(0.9, 0.95)]
[2023-04-19 18:02:24,489] [INFO] [timer.py:199:stop] epoch=0/micro_step=2660/global_step=1330, RunningAvgSamplesPerSec=12.297245436028547, CurrSamplesPerSec=12.321097156185356, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:02:50,544] [INFO] [logging.py:96:log_dist] [Rank 0] step=1340, skipped=26, lr=[0.00047851409599768043], mom=[(0.9, 0.95)]
[2023-04-19 18:02:50,545] [INFO] [timer.py:199:stop] epoch=0/micro_step=2680/global_step=1340, RunningAvgSamplesPerSec=12.297227368370496, CurrSamplesPerSec=12.2613119643179, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:03:17,310] [INFO] [logging.py:96:log_dist] [Rank 0] step=1350, skipped=26, lr=[0.0004723808222899481], mom=[(0.9, 0.95)]
[2023-04-19 18:03:17,311] [INFO] [timer.py:199:stop] epoch=0/micro_step=2700/global_step=1350, RunningAvgSamplesPerSec=12.294722758257807, CurrSamplesPerSec=12.307697273572408, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:03:43,362] [INFO] [logging.py:96:log_dist] [Rank 0] step=1360, skipped=26, lr=[0.0004662517144353085], mom=[(0.9, 0.95)]
[2023-04-19 18:03:43,363] [INFO] [timer.py:199:stop] epoch=0/micro_step=2720/global_step=1360, RunningAvgSamplesPerSec=12.294736732905998, CurrSamplesPerSec=12.305249806208746, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:04:10,013] [INFO] [logging.py:96:log_dist] [Rank 0] step=1370, skipped=26, lr=[0.0004601276968987546], mom=[(0.9, 0.95)]
[2023-04-19 18:04:10,014] [INFO] [timer.py:199:stop] epoch=0/micro_step=2740/global_step=1370, RunningAvgSamplesPerSec=12.292682779748246, CurrSamplesPerSec=12.342967791868034, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:04:36,396] [INFO] [logging.py:96:log_dist] [Rank 0] step=1380, skipped=26, lr=[0.0004540096933774962], mom=[(0.9, 0.95)]
[2023-04-19 18:04:36,396] [INFO] [timer.py:199:stop] epoch=0/micro_step=2760/global_step=1380, RunningAvgSamplesPerSec=12.291579956405803, CurrSamplesPerSec=12.317193944852322, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:05:02,819] [INFO] [logging.py:96:log_dist] [Rank 0] step=1390, skipped=26, lr=[0.00044789862666163807], mom=[(0.9, 0.95)]
[2023-04-19 18:05:02,819] [INFO] [timer.py:199:stop] epoch=0/micro_step=2780/global_step=1390, RunningAvgSamplesPerSec=12.290354577889605, CurrSamplesPerSec=12.290194891983273, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:05:29,595] [INFO] [logging.py:96:log_dist] [Rank 0] step=1400, skipped=26, lr=[0.0004417954184949932], mom=[(0.9, 0.95)]
[2023-04-19 18:05:29,596] [INFO] [timer.py:199:stop] epoch=0/micro_step=2800/global_step=1400, RunningAvgSamplesPerSec=12.287955655202952, CurrSamplesPerSec=12.235999243692683, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:05:55,671] [INFO] [logging.py:96:log_dist] [Rank 0] step=1410, skipped=26, lr=[0.0004357009894360553], mom=[(0.9, 0.95)]
[2023-04-19 18:05:55,671] [INFO] [timer.py:199:stop] epoch=0/micro_step=2820/global_step=1410, RunningAvgSamplesPerSec=12.287937989215635, CurrSamplesPerSec=12.295943882201728, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:06:22,415] [INFO] [logging.py:96:log_dist] [Rank 0] step=1420, skipped=26, lr=[0.0004296162587191479], mom=[(0.9, 0.95)]
[2023-04-19 18:06:22,416] [INFO] [timer.py:199:stop] epoch=0/micro_step=2840/global_step=1420, RunningAvgSamplesPerSec=12.285696192675177, CurrSamplesPerSec=12.326868307105308, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:06:40,557] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:06:43,112] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:06:48,337] [INFO] [logging.py:96:log_dist] [Rank 0] step=1430, skipped=28, lr=[0.0004247560737470216], mom=[(0.9, 0.95)]
[2023-04-19 18:06:48,338] [INFO] [timer.py:199:stop] epoch=0/micro_step=2860/global_step=1430, RunningAvgSamplesPerSec=12.286200975609571, CurrSamplesPerSec=12.302398476683939, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:07:15,113] [INFO] [logging.py:96:log_dist] [Rank 0] step=1440, skipped=28, lr=[0.00041869111175856633], mom=[(0.9, 0.95)]
[2023-04-19 18:07:15,114] [INFO] [timer.py:199:stop] epoch=0/micro_step=2880/global_step=1440, RunningAvgSamplesPerSec=12.283901533897822, CurrSamplesPerSec=12.290463868931733, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:07:41,149] [INFO] [logging.py:96:log_dist] [Rank 0] step=1450, skipped=28, lr=[0.00041263841374433654], mom=[(0.9, 0.95)]
[2023-04-19 18:07:41,149] [INFO] [timer.py:199:stop] epoch=0/micro_step=2900/global_step=1450, RunningAvgSamplesPerSec=12.284042842085487, CurrSamplesPerSec=12.325609509044535, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:08:07,778] [INFO] [logging.py:96:log_dist] [Rank 0] step=1460, skipped=28, lr=[0.00040659889264428324], mom=[(0.9, 0.95)]
[2023-04-19 18:08:07,779] [INFO] [timer.py:199:stop] epoch=0/micro_step=2920/global_step=1460, RunningAvgSamplesPerSec=12.282261851329789, CurrSamplesPerSec=12.314158567797463, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:08:34,176] [INFO] [logging.py:96:log_dist] [Rank 0] step=1470, skipped=28, lr=[0.0004005734594108583], mom=[(0.9, 0.95)]
[2023-04-19 18:08:34,177] [INFO] [timer.py:199:stop] epoch=0/micro_step=2940/global_step=1470, RunningAvgSamplesPerSec=12.28124751646962, CurrSamplesPerSec=12.284246646807013, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:09:00,567] [INFO] [logging.py:96:log_dist] [Rank 0] step=1480, skipped=28, lr=[0.00039456302287161396], mom=[(0.9, 0.95)]
[2023-04-19 18:09:00,567] [INFO] [timer.py:199:stop] epoch=0/micro_step=2960/global_step=1480, RunningAvgSamplesPerSec=12.280273099429602, CurrSamplesPerSec=12.304348471794587, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:09:27,304] [INFO] [logging.py:96:log_dist] [Rank 0] step=1490, skipped=28, lr=[0.0003885684895921226], mom=[(0.9, 0.95)]
[2023-04-19 18:09:27,304] [INFO] [timer.py:199:stop] epoch=0/micro_step=2980/global_step=1490, RunningAvgSamplesPerSec=12.278213162378892, CurrSamplesPerSec=12.288593653679008, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:09:53,333] [INFO] [logging.py:96:log_dist] [Rank 0] step=1500, skipped=28, lr=[0.0003825907637392375], mom=[(0.9, 0.95)]
[2023-04-19 18:09:53,334] [INFO] [timer.py:199:stop] epoch=0/micro_step=3000/global_step=1500, RunningAvgSamplesPerSec=12.27840720321145, CurrSamplesPerSec=12.275688721970516, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:10:20,080] [INFO] [logging.py:96:log_dist] [Rank 0] step=1510, skipped=28, lr=[0.0003766307469447161], mom=[(0.9, 0.95)]
[2023-04-19 18:10:20,080] [INFO] [timer.py:199:stop] epoch=0/micro_step=3020/global_step=1510, RunningAvgSamplesPerSec=12.276358165025238, CurrSamplesPerSec=12.341332347628354, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:10:46,100] [INFO] [logging.py:96:log_dist] [Rank 0] step=1520, skipped=28, lr=[0.00037068933816922456], mom=[(0.9, 0.95)]
[2023-04-19 18:10:46,100] [INFO] [timer.py:199:stop] epoch=0/micro_step=3040/global_step=1520, RunningAvgSamplesPerSec=12.276591206833402, CurrSamplesPerSec=12.318812821547843, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:11:10,214] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:11:12,767] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:11:12,767] [INFO] [logging.py:96:log_dist] [Rank 0] step=1530, skipped=30, lr=[0.000365950211235768], mom=[(0.9, 0.95)]
[2023-04-19 18:11:12,768] [INFO] [timer.py:199:stop] epoch=0/micro_step=3060/global_step=1530, RunningAvgSamplesPerSec=12.274823812996173, CurrSamplesPerSec=12.545723730485774, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:11:39,159] [INFO] [logging.py:96:log_dist] [Rank 0] step=1540, skipped=30, lr=[0.00036004455323017474], mom=[(0.9, 0.95)]
[2023-04-19 18:11:39,159] [INFO] [timer.py:199:stop] epoch=0/micro_step=3080/global_step=1540, RunningAvgSamplesPerSec=12.273924370839671, CurrSamplesPerSec=10.841243528321511, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:12:05,392] [INFO] [logging.py:96:log_dist] [Rank 0] step=1550, skipped=30, lr=[0.00035416000497074865], mom=[(0.9, 0.95)]
[2023-04-19 18:12:05,393] [INFO] [timer.py:199:stop] epoch=0/micro_step=3100/global_step=1550, RunningAvgSamplesPerSec=12.273519460152688, CurrSamplesPerSec=12.274678332960356, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:12:31,989] [INFO] [logging.py:96:log_dist] [Rank 0] step=1560, skipped=30, lr=[0.0003482974540350933], mom=[(0.9, 0.95)]
[2023-04-19 18:12:31,990] [INFO] [timer.py:199:stop] epoch=0/micro_step=3120/global_step=1560, RunningAvgSamplesPerSec=12.272017635829767, CurrSamplesPerSec=10.848107117940044, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:12:57,722] [INFO] [logging.py:96:log_dist] [Rank 0] step=1570, skipped=30, lr=[0.0003424577846829144], mom=[(0.9, 0.95)]
[2023-04-19 18:12:57,722] [INFO] [timer.py:199:stop] epoch=0/micro_step=3140/global_step=1570, RunningAvgSamplesPerSec=12.273125881399084, CurrSamplesPerSec=12.488360282731884, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:13:24,190] [INFO] [logging.py:96:log_dist] [Rank 0] step=1580, skipped=30, lr=[0.00033664187772264466], mom=[(0.9, 0.95)]
[2023-04-19 18:13:24,190] [INFO] [timer.py:199:stop] epoch=0/micro_step=3160/global_step=1580, RunningAvgSamplesPerSec=12.27202700089158, CurrSamplesPerSec=12.450442790397208, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:13:49,948] [INFO] [logging.py:96:log_dist] [Rank 0] step=1590, skipped=30, lr=[0.00033085061037859], mom=[(0.9, 0.95)]
[2023-04-19 18:13:49,949] [INFO] [timer.py:199:stop] epoch=0/micro_step=3180/global_step=1590, RunningAvgSamplesPerSec=12.27304390587419, CurrSamplesPerSec=12.406213786289506, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:14:16,439] [INFO] [logging.py:96:log_dist] [Rank 0] step=1600, skipped=30, lr=[0.00032508485615861607], mom=[(0.9, 0.95)]
[2023-04-19 18:14:16,439] [INFO] [timer.py:199:stop] epoch=0/micro_step=3200/global_step=1600, RunningAvgSamplesPerSec=12.271896058667723, CurrSamplesPerSec=12.42768362926357, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:14:42,173] [INFO] [logging.py:96:log_dist] [Rank 0] step=1610, skipped=30, lr=[0.0003193454847223962], mom=[(0.9, 0.95)]
[2023-04-19 18:14:42,174] [INFO] [timer.py:199:stop] epoch=0/micro_step=3220/global_step=1610, RunningAvgSamplesPerSec=12.272971178673968, CurrSamplesPerSec=12.442486870831228, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:15:08,528] [INFO] [logging.py:96:log_dist] [Rank 0] step=1620, skipped=30, lr=[0.00031363336175023725], mom=[(0.9, 0.95)]
[2023-04-19 18:15:08,528] [INFO] [timer.py:199:stop] epoch=0/micro_step=3240/global_step=1620, RunningAvgSamplesPerSec=12.27222947378135, CurrSamplesPerSec=12.439632699307893, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:15:34,663] [INFO] [logging.py:96:log_dist] [Rank 0] step=1630, skipped=30, lr=[0.0003079493488125092], mom=[(0.9, 0.95)]
[2023-04-19 18:15:34,664] [INFO] [timer.py:199:stop] epoch=0/micro_step=3260/global_step=1630, RunningAvgSamplesPerSec=12.272130563979738, CurrSamplesPerSec=12.395891314029205, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:15:37,182] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:15:39,970] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:16:00,634] [INFO] [logging.py:96:log_dist] [Rank 0] step=1640, skipped=32, lr=[0.0003034229539589651], mom=[(0.9, 0.95)]
[2023-04-19 18:16:00,635] [INFO] [timer.py:199:stop] epoch=0/micro_step=3280/global_step=1640, RunningAvgSamplesPerSec=12.272505412199054, CurrSamplesPerSec=12.391153478786137, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:16:27,180] [INFO] [logging.py:96:log_dist] [Rank 0] step=1650, skipped=32, lr=[0.00029779169662424564], mom=[(0.9, 0.95)]
[2023-04-19 18:16:27,180] [INFO] [timer.py:199:stop] epoch=0/micro_step=3300/global_step=1650, RunningAvgSamplesPerSec=12.271236433244209, CurrSamplesPerSec=10.890016115419574, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:16:52,970] [INFO] [logging.py:96:log_dist] [Rank 0] step=1660, skipped=32, lr=[0.00029219093875243143], mom=[(0.9, 0.95)]
[2023-04-19 18:16:52,971] [INFO] [timer.py:199:stop] epoch=0/micro_step=3320/global_step=1660, RunningAvgSamplesPerSec=12.27212462539587, CurrSamplesPerSec=12.348976463033916, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:17:19,514] [INFO] [logging.py:96:log_dist] [Rank 0] step=1670, skipped=32, lr=[0.0002866215251164824], mom=[(0.9, 0.95)]
[2023-04-19 18:17:19,515] [INFO] [timer.py:199:stop] epoch=0/micro_step=3340/global_step=1670, RunningAvgSamplesPerSec=12.270876288262468, CurrSamplesPerSec=12.430595638622705, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:17:45,354] [INFO] [logging.py:96:log_dist] [Rank 0] step=1680, skipped=32, lr=[0.0002810842957616477], mom=[(0.9, 0.95)]
[2023-04-19 18:17:45,355] [INFO] [timer.py:199:stop] epoch=0/micro_step=3360/global_step=1680, RunningAvgSamplesPerSec=12.271617283094267, CurrSamplesPerSec=12.406374333326339, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:18:11,907] [INFO] [logging.py:96:log_dist] [Rank 0] step=1690, skipped=32, lr=[0.00027558008587876047], mom=[(0.9, 0.95)]
[2023-04-19 18:18:11,907] [INFO] [timer.py:199:stop] epoch=0/micro_step=3380/global_step=1690, RunningAvgSamplesPerSec=12.270363834350324, CurrSamplesPerSec=12.39498237596127, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:18:37,648] [INFO] [logging.py:96:log_dist] [Rank 0] step=1700, skipped=32, lr=[0.00027010972567826367], mom=[(0.9, 0.95)]
[2023-04-19 18:18:37,649] [INFO] [timer.py:199:stop] epoch=0/micro_step=3400/global_step=1700, RunningAvgSamplesPerSec=12.271373139771677, CurrSamplesPerSec=12.584368640670158, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:19:03,554] [INFO] [logging.py:96:log_dist] [Rank 0] step=1710, skipped=32, lr=[0.000264674040264988], mom=[(0.9, 0.95)]
[2023-04-19 18:19:03,554] [INFO] [timer.py:199:stop] epoch=0/micro_step=3420/global_step=1710, RunningAvgSamplesPerSec=12.271917693197654, CurrSamplesPerSec=12.828423573004878, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:19:28,898] [INFO] [logging.py:96:log_dist] [Rank 0] step=1720, skipped=32, lr=[0.00025927384951370127], mom=[(0.9, 0.95)]
[2023-04-19 18:19:28,899] [INFO] [timer.py:199:stop] epoch=0/micro_step=3440/global_step=1720, RunningAvgSamplesPerSec=12.273993814762228, CurrSamplesPerSec=12.802104838251223, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:19:54,046] [INFO] [logging.py:96:log_dist] [Rank 0] step=1730, skipped=32, lr=[0.0002539099679454425], mom=[(0.9, 0.95)]
[2023-04-19 18:19:54,047] [INFO] [timer.py:199:stop] epoch=0/micro_step=3460/global_step=1730, RunningAvgSamplesPerSec=12.276580675964897, CurrSamplesPerSec=12.900282740307876, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:20:01,466] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:20:03,937] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:20:19,636] [INFO] [logging.py:96:log_dist] [Rank 0] step=1740, skipped=34, lr=[0.00024964554916762446], mom=[(0.9, 0.95)]
[2023-04-19 18:20:19,637] [INFO] [timer.py:199:stop] epoch=0/micro_step=3480/global_step=1740, RunningAvgSamplesPerSec=12.277943442484174, CurrSamplesPerSec=12.880564950258988, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:20:44,554] [INFO] [logging.py:96:log_dist] [Rank 0] step=1750, skipped=34, lr=[0.00024434905916265827], mom=[(0.9, 0.95)]
[2023-04-19 18:20:44,555] [INFO] [timer.py:199:stop] epoch=0/micro_step=3500/global_step=1750, RunningAvgSamplesPerSec=12.281099911613431, CurrSamplesPerSec=12.852529143234488, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:21:10,261] [INFO] [logging.py:96:log_dist] [Rank 0] step=1760, skipped=34, lr=[0.00023909112947522872], mom=[(0.9, 0.95)]
[2023-04-19 18:21:10,262] [INFO] [timer.py:199:stop] epoch=0/micro_step=3520/global_step=1760, RunningAvgSamplesPerSec=12.282106025091206, CurrSamplesPerSec=12.809001687377384, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:21:35,230] [INFO] [logging.py:96:log_dist] [Rank 0] step=1770, skipped=34, lr=[0.00023387255316886947], mom=[(0.9, 0.95)]
[2023-04-19 18:21:35,231] [INFO] [timer.py:199:stop] epoch=0/micro_step=3540/global_step=1770, RunningAvgSamplesPerSec=12.285070635156188, CurrSamplesPerSec=12.802605510726918, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:22:00,969] [INFO] [logging.py:96:log_dist] [Rank 0] step=1780, skipped=34, lr=[0.00022869411737136774], mom=[(0.9, 0.95)]
[2023-04-19 18:22:00,969] [INFO] [timer.py:199:stop] epoch=0/micro_step=3560/global_step=1780, RunningAvgSamplesPerSec=12.285961243756674, CurrSamplesPerSec=12.798800161308426, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:22:26,394] [INFO] [logging.py:96:log_dist] [Rank 0] step=1790, skipped=34, lr=[0.0002235566031560417], mom=[(0.9, 0.95)]
[2023-04-19 18:22:26,395] [INFO] [timer.py:199:stop] epoch=0/micro_step=3580/global_step=1790, RunningAvgSamplesPerSec=12.287666145186579, CurrSamplesPerSec=11.188044943992558, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:22:51,936] [INFO] [logging.py:96:log_dist] [Rank 0] step=1800, skipped=34, lr=[0.00021846078542393004], mom=[(0.9, 0.95)]
[2023-04-19 18:22:51,936] [INFO] [timer.py:199:stop] epoch=0/micro_step=3600/global_step=1800, RunningAvgSamplesPerSec=12.289049568018969, CurrSamplesPerSec=12.733015954391846, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:23:17,617] [INFO] [logging.py:96:log_dist] [Rank 0] step=1810, skipped=34, lr=[0.00021340743278691076], mom=[(0.9, 0.95)]
[2023-04-19 18:23:17,617] [INFO] [timer.py:199:stop] epoch=0/micro_step=3620/global_step=1810, RunningAvgSamplesPerSec=12.290053744673086, CurrSamplesPerSec=12.60355859829003, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:23:43,421] [INFO] [logging.py:96:log_dist] [Rank 0] step=1820, skipped=34, lr=[0.00020839730745177148], mom=[(0.9, 0.95)]
[2023-04-19 18:23:43,421] [INFO] [timer.py:199:stop] epoch=0/micro_step=3640/global_step=1820, RunningAvgSamplesPerSec=12.290727365115005, CurrSamplesPerSec=12.491374039968793, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:24:09,755] [INFO] [logging.py:96:log_dist] [Rank 0] step=1830, skipped=34, lr=[0.00020343116510524367], mom=[(0.9, 0.95)]
[2023-04-19 18:24:09,756] [INFO] [timer.py:199:stop] epoch=0/micro_step=3660/global_step=1830, RunningAvgSamplesPerSec=12.290024273445455, CurrSamplesPerSec=12.415638048515792, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:24:22,647] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:24:25,197] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:24:35,610] [INFO] [logging.py:96:log_dist] [Rank 0] step=1840, skipped=36, lr=[0.00019949042256902537], mom=[(0.9, 0.95)]
[2023-04-19 18:24:35,610] [INFO] [timer.py:199:stop] epoch=0/micro_step=3680/global_step=1840, RunningAvgSamplesPerSec=12.290559956150119, CurrSamplesPerSec=12.350383229989983, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:25:02,172] [INFO] [logging.py:96:log_dist] [Rank 0] step=1850, skipped=36, lr=[0.00019460533268455865], mom=[(0.9, 0.95)]
[2023-04-19 18:25:02,173] [INFO] [timer.py:199:stop] epoch=0/micro_step=3700/global_step=1850, RunningAvgSamplesPerSec=12.289282459116265, CurrSamplesPerSec=12.435905221269186, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:25:27,919] [INFO] [logging.py:96:log_dist] [Rank 0] step=1860, skipped=36, lr=[0.00018976630605848356], mom=[(0.9, 0.95)]
[2023-04-19 18:25:27,920] [INFO] [timer.py:199:stop] epoch=0/micro_step=3720/global_step=1860, RunningAvgSamplesPerSec=12.290090474590235, CurrSamplesPerSec=12.435068747489805, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:25:54,350] [INFO] [logging.py:96:log_dist] [Rank 0] step=1870, skipped=36, lr=[0.00018497407257038722], mom=[(0.9, 0.95)]
[2023-04-19 18:25:54,351] [INFO] [timer.py:199:stop] epoch=0/micro_step=3740/global_step=1870, RunningAvgSamplesPerSec=12.28916153999188, CurrSamplesPerSec=12.468483660129504, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:26:20,422] [INFO] [logging.py:96:log_dist] [Rank 0] step=1880, skipped=36, lr=[0.00018022935504195952], mom=[(0.9, 0.95)]
[2023-04-19 18:26:20,422] [INFO] [timer.py:199:stop] epoch=0/micro_step=3760/global_step=1880, RunningAvgSamplesPerSec=12.289146106288744, CurrSamplesPerSec=10.895669559644977, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:26:46,605] [INFO] [logging.py:96:log_dist] [Rank 0] step=1890, skipped=36, lr=[0.00017553286912796773], mom=[(0.9, 0.95)]
[2023-04-19 18:26:46,605] [INFO] [timer.py:199:stop] epoch=0/micro_step=3780/global_step=1890, RunningAvgSamplesPerSec=12.288853181453334, CurrSamplesPerSec=12.376522274843671, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:27:12,953] [INFO] [logging.py:96:log_dist] [Rank 0] step=1900, skipped=36, lr=[0.00017088532320831245], mom=[(0.9, 0.95)]
[2023-04-19 18:27:12,954] [INFO] [timer.py:199:stop] epoch=0/micro_step=3800/global_step=1900, RunningAvgSamplesPerSec=12.288151161040204, CurrSamplesPerSec=11.314906634422599, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:27:38,340] [INFO] [logging.py:96:log_dist] [Rank 0] step=1910, skipped=36, lr=[0.00016628741828118255], mom=[(0.9, 0.95)]
[2023-04-19 18:27:38,340] [INFO] [timer.py:199:stop] epoch=0/micro_step=3820/global_step=1910, RunningAvgSamplesPerSec=12.289834917827946, CurrSamplesPerSec=12.758622957963134, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:28:04,093] [INFO] [logging.py:96:log_dist] [Rank 0] step=1920, skipped=36, lr=[0.0001617398478573211], mom=[(0.9, 0.95)]
[2023-04-19 18:28:04,094] [INFO] [timer.py:199:stop] epoch=0/micro_step=3840/global_step=1920, RunningAvgSamplesPerSec=12.290598323679253, CurrSamplesPerSec=12.841313334019006, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:28:29,058] [INFO] [logging.py:96:log_dist] [Rank 0] step=1930, skipped=36, lr=[0.0001572432978554223], mom=[(0.9, 0.95)]
[2023-04-19 18:28:29,058] [INFO] [timer.py:199:stop] epoch=0/micro_step=3860/global_step=1930, RunningAvgSamplesPerSec=12.293287579333615, CurrSamplesPerSec=12.792861649178567, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:28:47,200] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:28:49,671] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:28:54,671] [INFO] [logging.py:96:log_dist] [Rank 0] step=1940, skipped=38, lr=[0.0001536832485848859], mom=[(0.9, 0.95)]
[2023-04-19 18:28:54,671] [INFO] [timer.py:199:stop] epoch=0/micro_step=3880/global_step=1940, RunningAvgSamplesPerSec=12.294367966683168, CurrSamplesPerSec=12.86009034984407, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:29:19,558] [INFO] [logging.py:96:log_dist] [Rank 0] step=1950, skipped=38, lr=[0.00014928023922823442], mom=[(0.9, 0.95)]
[2023-04-19 18:29:19,558] [INFO] [timer.py:199:stop] epoch=0/micro_step=3900/global_step=1950, RunningAvgSamplesPerSec=12.29720127164094, CurrSamplesPerSec=12.879749164030441, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:29:45,078] [INFO] [logging.py:96:log_dist] [Rank 0] step=1960, skipped=38, lr=[0.00014493012960000785], mom=[(0.9, 0.95)]
[2023-04-19 18:29:45,079] [INFO] [timer.py:199:stop] epoch=0/micro_step=3920/global_step=1960, RunningAvgSamplesPerSec=12.298476526249685, CurrSamplesPerSec=12.867855376739639, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:30:10,380] [INFO] [logging.py:96:log_dist] [Rank 0] step=1970, skipped=38, lr=[0.0001406335758355134], mom=[(0.9, 0.95)]
[2023-04-19 18:30:10,380] [INFO] [timer.py:199:stop] epoch=0/micro_step=3940/global_step=1970, RunningAvgSamplesPerSec=12.300264143525318, CurrSamplesPerSec=12.820006808415691, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:30:35,732] [INFO] [logging.py:96:log_dist] [Rank 0] step=1980, skipped=38, lr=[0.00013639122599212533], mom=[(0.9, 0.95)]
[2023-04-19 18:30:35,733] [INFO] [timer.py:199:stop] epoch=0/micro_step=3960/global_step=1980, RunningAvgSamplesPerSec=12.301912515264485, CurrSamplesPerSec=12.802970659982275, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:31:01,381] [INFO] [logging.py:96:log_dist] [Rank 0] step=1990, skipped=38, lr=[0.00013220371995153736], mom=[(0.9, 0.95)]
[2023-04-19 18:31:01,382] [INFO] [timer.py:199:stop] epoch=0/micro_step=3980/global_step=1990, RunningAvgSamplesPerSec=12.302840564663645, CurrSamplesPerSec=11.593263562391549, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:31:26,506] [INFO] [logging.py:96:log_dist] [Rank 0] step=2000, skipped=38, lr=[0.00012807168932324857], mom=[(0.9, 0.95)]
[2023-04-19 18:31:26,506] [INFO] [timer.py:199:stop] epoch=0/micro_step=4000/global_step=2000, RunningAvgSamplesPerSec=12.304999928758503, CurrSamplesPerSec=12.715702879906292, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:31:52,481] [INFO] [logging.py:96:log_dist] [Rank 0] step=2010, skipped=38, lr=[0.0001239957573492957], mom=[(0.9, 0.95)]
[2023-04-19 18:31:52,481] [INFO] [timer.py:199:stop] epoch=0/micro_step=4020/global_step=2010, RunningAvgSamplesPerSec=12.305134776463118, CurrSamplesPerSec=12.599764184596898, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:32:17,970] [INFO] [logging.py:96:log_dist] [Rank 0] step=2020, skipped=38, lr=[0.00011997653881024884], mom=[(0.9, 0.95)]
[2023-04-19 18:32:17,971] [INFO] [timer.py:199:stop] epoch=0/micro_step=4040/global_step=2020, RunningAvgSamplesPerSec=12.306405867559443, CurrSamplesPerSec=12.496697285427834, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:32:44,382] [INFO] [logging.py:96:log_dist] [Rank 0] step=2030, skipped=38, lr=[0.0001160146399324833], mom=[(0.9, 0.95)]
[2023-04-19 18:32:44,383] [INFO] [timer.py:199:stop] epoch=0/micro_step=4060/global_step=2030, RunningAvgSamplesPerSec=12.305514093554024, CurrSamplesPerSec=12.39382407379021, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:33:07,621] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:33:10,518] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:33:10,518] [INFO] [logging.py:96:log_dist] [Rank 0] step=2040, skipped=40, lr=[0.00011288679285345288], mom=[(0.9, 0.95)]
[2023-04-19 18:33:10,518] [INFO] [timer.py:199:stop] epoch=0/micro_step=4080/global_step=2040, RunningAvgSamplesPerSec=12.305270434756762, CurrSamplesPerSec=11.058220762964236, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:33:36,786] [INFO] [logging.py:96:log_dist] [Rank 0] step=2050, skipped=40, lr=[0.0001090295694020207], mom=[(0.9, 0.95)]
[2023-04-19 18:33:36,786] [INFO] [timer.py:199:stop] epoch=0/micro_step=4100/global_step=2050, RunningAvgSamplesPerSec=12.304723993392827, CurrSamplesPerSec=12.338405292495112, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:34:02,975] [INFO] [logging.py:96:log_dist] [Rank 0] step=2060, skipped=40, lr=[0.00010523131676408154], mom=[(0.9, 0.95)]
[2023-04-19 18:34:02,975] [INFO] [timer.py:199:stop] epoch=0/micro_step=4120/global_step=2060, RunningAvgSamplesPerSec=12.304364466002099, CurrSamplesPerSec=12.451194702243312, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:34:29,152] [INFO] [logging.py:96:log_dist] [Rank 0] step=2070, skipped=40, lr=[0.00010149260783730319], mom=[(0.9, 0.95)]
[2023-04-19 18:34:29,153] [INFO] [timer.py:199:stop] epoch=0/micro_step=4140/global_step=2070, RunningAvgSamplesPerSec=12.304034186898377, CurrSamplesPerSec=12.411747026891463, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:34:55,549] [INFO] [logging.py:96:log_dist] [Rank 0] step=2080, skipped=40, lr=[9.781400653826244e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:34:55,550] [INFO] [timer.py:199:stop] epoch=0/micro_step=4160/global_step=2080, RunningAvgSamplesPerSec=12.303206574085898, CurrSamplesPerSec=12.411290230109326, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:35:21,383] [INFO] [logging.py:96:log_dist] [Rank 0] step=2090, skipped=40, lr=[9.419606771738853e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:35:21,383] [INFO] [timer.py:199:stop] epoch=0/micro_step=4180/global_step=2090, RunningAvgSamplesPerSec=12.30366604428486, CurrSamplesPerSec=12.406835355771703, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:35:47,968] [INFO] [logging.py:96:log_dist] [Rank 0] step=2100, skipped=40, lr=[9.063933707527306e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:35:47,968] [INFO] [timer.py:199:stop] epoch=0/micro_step=4200/global_step=2100, RunningAvgSamplesPerSec=12.302425094480283, CurrSamplesPerSec=12.383200007011915, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:36:13,793] [INFO] [logging.py:96:log_dist] [Rank 0] step=2110, skipped=40, lr=[8.714435108036234e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:36:13,794] [INFO] [timer.py:199:stop] epoch=0/micro_step=4220/global_step=2110, RunningAvgSamplesPerSec=12.302901308765746, CurrSamplesPerSec=12.434363708237937, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:36:40,308] [INFO] [logging.py:96:log_dist] [Rank 0] step=2120, skipped=40, lr=[8.371163688803967e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:36:40,308] [INFO] [timer.py:199:stop] epoch=0/micro_step=4240/global_step=2120, RunningAvgSamplesPerSec=12.301832484359094, CurrSamplesPerSec=12.420096949094322, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:37:06,496] [INFO] [logging.py:96:log_dist] [Rank 0] step=2130, skipped=40, lr=[8.034171226111403e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:37:06,497] [INFO] [timer.py:199:stop] epoch=0/micro_step=4260/global_step=2130, RunningAvgSamplesPerSec=12.301499367685778, CurrSamplesPerSec=10.856264810636182, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:37:32,691] [INFO] [logging.py:96:log_dist] [Rank 0] step=2140, skipped=40, lr=[7.703508549172528e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:37:32,691] [INFO] [timer.py:199:stop] epoch=0/micro_step=4280/global_step=2140, RunningAvgSamplesPerSec=12.30115622408466, CurrSamplesPerSec=12.401573479735115, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:37:35,215] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:37:37,759] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:37:58,792] [INFO] [logging.py:96:log_dist] [Rank 0] step=2150, skipped=42, lr=[7.443569401286737e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:37:58,792] [INFO] [timer.py:199:stop] epoch=0/micro_step=4300/global_step=2150, RunningAvgSamplesPerSec=12.30102199734571, CurrSamplesPerSec=12.400159610180129, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:38:24,948] [INFO] [logging.py:96:log_dist] [Rank 0] step=2160, skipped=42, lr=[7.124425376007727e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:38:24,948] [INFO] [timer.py:199:stop] epoch=0/micro_step=4320/global_step=2160, RunningAvgSamplesPerSec=12.300768461536611, CurrSamplesPerSec=12.453067368968957, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:38:51,245] [INFO] [logging.py:96:log_dist] [Rank 0] step=2170, skipped=42, lr=[6.811748355178887e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:38:51,245] [INFO] [timer.py:199:stop] epoch=0/micro_step=4340/global_step=2170, RunningAvgSamplesPerSec=12.300209402649584, CurrSamplesPerSec=12.43781132701424, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:39:17,070] [INFO] [logging.py:96:log_dist] [Rank 0] step=2180, skipped=42, lr=[6.505585500469818e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:39:17,071] [INFO] [timer.py:199:stop] epoch=0/micro_step=4360/global_step=2180, RunningAvgSamplesPerSec=12.300679290112301, CurrSamplesPerSec=12.365838971239125, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:39:43,643] [INFO] [logging.py:96:log_dist] [Rank 0] step=2190, skipped=42, lr=[6.205982991006093e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:39:43,643] [INFO] [timer.py:199:stop] epoch=0/micro_step=4380/global_step=2190, RunningAvgSamplesPerSec=12.299530650271372, CurrSamplesPerSec=12.405328558682902, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:40:09,493] [INFO] [logging.py:96:log_dist] [Rank 0] step=2200, skipped=42, lr=[5.912986016403909e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:40:09,494] [INFO] [timer.py:199:stop] epoch=0/micro_step=4400/global_step=2200, RunningAvgSamplesPerSec=12.299945811894498, CurrSamplesPerSec=12.441138616114486, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:40:36,096] [INFO] [logging.py:96:log_dist] [Rank 0] step=2210, skipped=42, lr=[5.6266387699540786e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:40:36,097] [INFO] [timer.py:199:stop] epoch=0/micro_step=4420/global_step=2210, RunningAvgSamplesPerSec=12.298745310472013, CurrSamplesPerSec=12.415833295329127, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:41:02,293] [INFO] [logging.py:96:log_dist] [Rank 0] step=2220, skipped=42, lr=[5.346984441956315e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:41:02,293] [INFO] [timer.py:199:stop] epoch=0/micro_step=4440/global_step=2220, RunningAvgSamplesPerSec=12.298422423831754, CurrSamplesPerSec=12.331312379976227, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:41:28,489] [INFO] [logging.py:96:log_dist] [Rank 0] step=2230, skipped=42, lr=[5.074065213204676e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:41:28,490] [INFO] [timer.py:199:stop] epoch=0/micro_step=4460/global_step=2230, RunningAvgSamplesPerSec=12.298102818031259, CurrSamplesPerSec=12.428839061774376, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:41:54,606] [INFO] [logging.py:96:log_dist] [Rank 0] step=2240, skipped=42, lr=[4.8079222486253736e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:41:54,607] [INFO] [timer.py:199:stop] epoch=0/micro_step=4480/global_step=2240, RunningAvgSamplesPerSec=12.297953704777502, CurrSamplesPerSec=12.434558392459168, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:42:02,610] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:42:05,144] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:42:20,545] [INFO] [logging.py:96:log_dist] [Rank 0] step=2250, skipped=44, lr=[4.599913797658045e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:42:20,546] [INFO] [timer.py:199:stop] epoch=0/micro_step=4500/global_step=2250, RunningAvgSamplesPerSec=12.298179937217506, CurrSamplesPerSec=12.529763874087092, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:42:46,846] [INFO] [logging.py:96:log_dist] [Rank 0] step=2260, skipped=44, lr=[4.346068577864587e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:42:46,846] [INFO] [timer.py:199:stop] epoch=0/micro_step=4520/global_step=2260, RunningAvgSamplesPerSec=12.29764823685467, CurrSamplesPerSec=12.45570692530282, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:43:12,672] [INFO] [logging.py:96:log_dist] [Rank 0] step=2270, skipped=44, lr=[4.099109427360304e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:43:12,672] [INFO] [timer.py:199:stop] epoch=0/micro_step=4540/global_step=2270, RunningAvgSamplesPerSec=12.298109115305559, CurrSamplesPerSec=12.437736408563667, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:43:38,689] [INFO] [logging.py:96:log_dist] [Rank 0] step=2280, skipped=44, lr=[3.859073595463469e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:43:38,690] [INFO] [timer.py:199:stop] epoch=0/micro_step=4560/global_step=2280, RunningAvgSamplesPerSec=12.298170178178243, CurrSamplesPerSec=12.75117692923243, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:44:03,731] [INFO] [logging.py:96:log_dist] [Rank 0] step=2290, skipped=44, lr=[3.6259972872350666e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:44:03,732] [INFO] [timer.py:199:stop] epoch=0/micro_step=4580/global_step=2290, RunningAvgSamplesPerSec=12.300246104187035, CurrSamplesPerSec=12.824455816125798, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:44:29,392] [INFO] [logging.py:96:log_dist] [Rank 0] step=2300, skipped=44, lr=[3.399915658017838e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:44:29,392] [INFO] [timer.py:199:stop] epoch=0/micro_step=4600/global_step=2300, RunningAvgSamplesPerSec=12.301030032165718, CurrSamplesPerSec=12.871611794362979, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:44:54,682] [INFO] [logging.py:96:log_dist] [Rank 0] step=2310, skipped=44, lr=[3.1808628081338496e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:44:54,682] [INFO] [timer.py:199:stop] epoch=0/micro_step=4620/global_step=2310, RunningAvgSamplesPerSec=12.302568709380266, CurrSamplesPerSec=12.835298490770182, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:45:19,976] [INFO] [logging.py:96:log_dist] [Rank 0] step=2320, skipped=44, lr=[2.9688717777409667e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:45:19,976] [INFO] [timer.py:199:stop] epoch=0/micro_step=4640/global_step=2320, RunningAvgSamplesPerSec=12.304085416510999, CurrSamplesPerSec=12.840191724087525, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:45:45,627] [INFO] [logging.py:96:log_dist] [Rank 0] step=2330, skipped=44, lr=[2.7639745418494234e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:45:45,627] [INFO] [timer.py:199:stop] epoch=0/micro_step=4660/global_step=2330, RunningAvgSamplesPerSec=12.304862619859534, CurrSamplesPerSec=11.164547013836554, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:46:10,564] [INFO] [logging.py:96:log_dist] [Rank 0] step=2340, skipped=44, lr=[2.5662020054989298e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:46:10,564] [INFO] [timer.py:199:stop] epoch=0/micro_step=4680/global_step=2340, RunningAvgSamplesPerSec=12.307078782682758, CurrSamplesPerSec=12.811729488667604, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:46:23,358] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:46:25,838] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:46:36,126] [INFO] [logging.py:96:log_dist] [Rank 0] step=2350, skipped=46, lr=[2.413133842345444e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:46:36,126] [INFO] [timer.py:199:stop] epoch=0/micro_step=4700/global_step=2350, RunningAvgSamplesPerSec=12.308017841166846, CurrSamplesPerSec=12.765987834726452, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:47:01,158] [INFO] [logging.py:96:log_dist] [Rank 0] step=2360, skipped=46, lr=[2.2282602127670638e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:47:01,159] [INFO] [timer.py:199:stop] epoch=0/micro_step=4720/global_step=2360, RunningAvgSamplesPerSec=12.310010809005004, CurrSamplesPerSec=12.779279202937284, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:47:27,031] [INFO] [logging.py:96:log_dist] [Rank 0] step=2370, skipped=46, lr=[2.0505920855406757e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:47:27,032] [INFO] [timer.py:199:stop] epoch=0/micro_step=4740/global_step=2370, RunningAvgSamplesPerSec=12.310307228959495, CurrSamplesPerSec=12.691875719261018, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:47:52,702] [INFO] [logging.py:96:log_dist] [Rank 0] step=2380, skipped=46, lr=[1.8801562586877375e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:47:52,702] [INFO] [timer.py:199:stop] epoch=0/micro_step=4760/global_step=2380, RunningAvgSamplesPerSec=12.311004314974385, CurrSamplesPerSec=11.0915473904342, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:48:18,609] [INFO] [logging.py:96:log_dist] [Rank 0] step=2390, skipped=46, lr=[1.7169784393681164e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:48:18,610] [INFO] [timer.py:199:stop] epoch=0/micro_step=4780/global_step=2390, RunningAvgSamplesPerSec=12.311227600222733, CurrSamplesPerSec=12.524098052787979, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:48:44,677] [INFO] [logging.py:96:log_dist] [Rank 0] step=2400, skipped=46, lr=[1.561083240002592e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:48:44,678] [INFO] [timer.py:199:stop] epoch=0/micro_step=4800/global_step=2400, RunningAvgSamplesPerSec=12.311130099979922, CurrSamplesPerSec=12.407947914210096, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:49:10,952] [INFO] [logging.py:96:log_dist] [Rank 0] step=2410, skipped=46, lr=[1.4124941745605024e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:49:10,952] [INFO] [timer.py:199:stop] epoch=0/micro_step=4820/global_step=2410, RunningAvgSamplesPerSec=12.310627790060659, CurrSamplesPerSec=12.370306632484153, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:49:37,487] [INFO] [logging.py:96:log_dist] [Rank 0] step=2420, skipped=46, lr=[1.2712336550131598e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:49:37,487] [INFO] [timer.py:199:stop] epoch=0/micro_step=4840/global_step=2420, RunningAvgSamplesPerSec=12.309618788598172, CurrSamplesPerSec=10.852950064021522, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:50:03,211] [INFO] [logging.py:96:log_dist] [Rank 0] step=2430, skipped=46, lr=[1.1373229879533375e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:50:03,211] [INFO] [timer.py:199:stop] epoch=0/micro_step=4860/global_step=2430, RunningAvgSamplesPerSec=12.310200725412857, CurrSamplesPerSec=12.48376864028326, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:50:29,508] [INFO] [logging.py:96:log_dist] [Rank 0] step=2440, skipped=46, lr=[1.010782371381569e-05], mom=[(0.9, 0.95)]
[2023-04-19 18:50:29,508] [INFO] [timer.py:199:stop] epoch=0/micro_step=4880/global_step=2440, RunningAvgSamplesPerSec=12.309663735759242, CurrSamplesPerSec=12.454816932342066, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:50:47,517] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:50:50,067] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:50:55,269] [INFO] [logging.py:96:log_dist] [Rank 0] step=2450, skipped=48, lr=[9.14869177936145e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:50:55,269] [INFO] [timer.py:199:stop] epoch=0/micro_step=4900/global_step=2450, RunningAvgSamplesPerSec=12.31016926218093, CurrSamplesPerSec=12.382171843136206, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:51:21,646] [INFO] [logging.py:96:log_dist] [Rank 0] step=2460, skipped=48, lr=[8.016420010113156e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:51:21,647] [INFO] [timer.py:199:stop] epoch=0/micro_step=4920/global_step=2460, RunningAvgSamplesPerSec=12.309482308619254, CurrSamplesPerSec=12.48385456463192, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:51:47,716] [INFO] [logging.py:96:log_dist] [Rank 0] step=2470, skipped=48, lr=[6.958355059761279e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:51:47,717] [INFO] [timer.py:199:stop] epoch=0/micro_step=4940/global_step=2470, RunningAvgSamplesPerSec=12.309390904770943, CurrSamplesPerSec=12.388855674772541, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:52:13,820] [INFO] [logging.py:96:log_dist] [Rank 0] step=2480, skipped=48, lr=[5.974656518254129e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:52:13,820] [INFO] [timer.py:199:stop] epoch=0/micro_step=4960/global_step=2480, RunningAvgSamplesPerSec=12.309235890996996, CurrSamplesPerSec=12.403854224243707, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:52:40,021] [INFO] [logging.py:96:log_dist] [Rank 0] step=2490, skipped=48, lr=[5.06547275871333e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:52:40,021] [INFO] [timer.py:199:stop] epoch=0/micro_step=4980/global_step=2490, RunningAvgSamplesPerSec=12.308896336184107, CurrSamplesPerSec=12.31674295094959, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:53:06,296] [INFO] [logging.py:96:log_dist] [Rank 0] step=2500, skipped=48, lr=[4.23094091505416e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:53:06,297] [INFO] [timer.py:199:stop] epoch=0/micro_step=5000/global_step=2500, RunningAvgSamplesPerSec=12.30841818692135, CurrSamplesPerSec=12.305871454185846, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:53:32,845] [INFO] [logging.py:96:log_dist] [Rank 0] step=2510, skipped=48, lr=[3.471186861301545e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:53:32,846] [INFO] [timer.py:199:stop] epoch=0/micro_step=5020/global_step=2510, RunningAvgSamplesPerSec=12.307428673506953, CurrSamplesPerSec=12.437062183120354, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:53:58,554] [INFO] [logging.py:96:log_dist] [Rank 0] step=2520, skipped=48, lr=[2.7863251926040224e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:53:58,554] [INFO] [timer.py:199:stop] epoch=0/micro_step=5040/global_step=2520, RunningAvgSamplesPerSec=12.308026366186626, CurrSamplesPerSec=12.448089466013181, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:54:24,848] [INFO] [logging.py:96:log_dist] [Rank 0] step=2530, skipped=48, lr=[2.1764592079493996e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:54:24,848] [INFO] [timer.py:199:stop] epoch=0/micro_step=5060/global_step=2530, RunningAvgSamplesPerSec=12.307524238014608, CurrSamplesPerSec=12.462064247476162, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:54:50,593] [INFO] [logging.py:96:log_dist] [Rank 0] step=2540, skipped=48, lr=[1.6416808945838302e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:54:50,593] [INFO] [timer.py:199:stop] epoch=0/micro_step=5080/global_step=2540, RunningAvgSamplesPerSec=12.308049471202695, CurrSamplesPerSec=12.400358953137731, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
[2023-04-19 18:55:14,484] [INFO] [loss_scaler.py:188:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, but hysteresis is 2. Reducing hysteresis to 1
[2023-04-19 18:55:17,038] [INFO] [loss_scaler.py:181:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 131072, reducing to 65536
[2023-04-19 18:55:17,039] [INFO] [logging.py:96:log_dist] [Rank 0] step=2550, skipped=50, lr=[1.2679759526949552e-06], mom=[(0.9, 0.95)]
[2023-04-19 18:55:17,039] [INFO] [timer.py:199:stop] epoch=0/micro_step=5100/global_step=2550, RunningAvgSamplesPerSec=12.307268386762189, CurrSamplesPerSec=12.540417228668503, MemAllocated=1.95GB, MaxMemAllocated=13.62GB
***** Evaluating perplexity, Epoch 1/1 *****
Invalidate trace cache @ step 0: expected module 0, but got module 16
ppl: 1.6646381616592407
saving the final model ...
[2023-04-19 19:03:02,394] [INFO] [launch.py:460:main] Process 10813 exits successfully.
[2023-04-19 19:03:02,395] [INFO] [launch.py:460:main] Process 10814 exits successfully.
[2023-04-19 19:03:02,395] [INFO] [launch.py:460:main] Process 10815 exits successfully.
[2023-04-19 19:03:14,408] [INFO] [launch.py:460:main] Process 10812 exits successfully.