bbytxt commited on
Commit
44bad10
·
verified ·
1 Parent(s): 83a7379

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a68d62a187450491a0227a65fd962446bff7ec8501da15514ff27a50f8f1f19
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5676a540c78e4e87833d8992fc14f35323ee4d1eb61fe712130267b5cdf6a0b
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12a2af5846474703e996cae82c6f16e1e9e155f332058e0955e29c8f29327c9e
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24ba9fdb4e5ab57c25fe2bdb3ac4c4b8591c463057e3325c8d3d405bc7b963c
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c01d933c4608fec408bbac0ec6224131cfb9001b6f43cf86dfbfa03318baef4c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de101eccb7a7b22dcf273ae56649eafbcfc01285ec6df8e2fbee434f1994f3d9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.617767095565796,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.018758206715438003,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -373,6 +373,364 @@
373
  "eval_samples_per_second": 12.26,
374
  "eval_steps_per_second": 1.535,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.806557770009805e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.49005126953125,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.03751641343087601,
5
  "eval_steps": 50,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
373
  "eval_samples_per_second": 12.26,
374
  "eval_steps_per_second": 1.535,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.019133370849746763,
379
+ "grad_norm": 3.0668530464172363,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 1.6115,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.019508534984055526,
386
+ "grad_norm": 2.0221545696258545,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 1.4548,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.019883699118364285,
393
+ "grad_norm": 1.181392788887024,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 0.7772,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.020258863252673044,
400
+ "grad_norm": 1.638417363166809,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 0.9231,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.020634027386981803,
407
+ "grad_norm": 1.695191740989685,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 1.0114,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.021009191521290566,
414
+ "grad_norm": 1.8865028619766235,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 0.9822,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.021384355655599326,
421
+ "grad_norm": 2.3858845233917236,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 1.7195,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.021759519789908085,
428
+ "grad_norm": 1.7190085649490356,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 1.3282,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.022134683924216844,
435
+ "grad_norm": 2.187772750854492,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 1.09,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.022509848058525603,
442
+ "grad_norm": 1.8837783336639404,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 1.0456,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.022885012192834366,
449
+ "grad_norm": 1.810979962348938,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 1.2371,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.023260176327143126,
456
+ "grad_norm": 1.6549510955810547,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 1.2869,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.023635340461451885,
463
+ "grad_norm": 1.8585015535354614,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 1.2206,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.024010504595760644,
470
+ "grad_norm": 2.164670467376709,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 1.2996,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.024385668730069407,
477
+ "grad_norm": 2.0705413818359375,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 1.2158,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.024760832864378166,
484
+ "grad_norm": 1.8618977069854736,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 1.3169,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.025135996998686926,
491
+ "grad_norm": 2.355955123901367,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 1.1751,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.025511161132995685,
498
+ "grad_norm": 1.8614939451217651,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 1.3641,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.025886325267304444,
505
+ "grad_norm": 2.999551773071289,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 1.2753,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.026261489401613207,
512
+ "grad_norm": 1.9945933818817139,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 1.1216,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.026636653535921966,
519
+ "grad_norm": 1.8532859086990356,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 1.088,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.027011817670230726,
526
+ "grad_norm": 2.1395885944366455,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 1.0015,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.027386981804539485,
533
+ "grad_norm": 2.2408030033111572,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 1.108,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.027762145938848248,
540
+ "grad_norm": 2.0609114170074463,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 1.574,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.028137310073157007,
547
+ "grad_norm": 2.0313756465911865,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 1.1664,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.028512474207465766,
554
+ "grad_norm": 1.7218246459960938,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 1.3208,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.028887638341774526,
561
+ "grad_norm": 2.472414016723633,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 1.3203,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.029262802476083285,
568
+ "grad_norm": 1.6580557823181152,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 1.1601,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.029637966610392048,
575
+ "grad_norm": 1.7984857559204102,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 1.1257,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.030013130744700807,
582
+ "grad_norm": 2.6854803562164307,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 1.5246,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.030388294879009566,
589
+ "grad_norm": 2.4177401065826416,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 1.5478,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.030763459013318326,
596
+ "grad_norm": 2.418226957321167,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 1.5165,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.03113862314762709,
603
+ "grad_norm": 2.8937528133392334,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 1.7612,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.031513787281935844,
610
+ "grad_norm": 2.7434005737304688,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 1.7735,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.03188895141624461,
617
+ "grad_norm": 2.3153278827667236,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 1.4117,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.03226411555055337,
624
+ "grad_norm": 2.19724440574646,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 1.5057,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.032639279684862126,
631
+ "grad_norm": 4.022721290588379,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 1.4694,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.03301444381917089,
638
+ "grad_norm": 2.6987545490264893,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 1.8611,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.033389607953479644,
645
+ "grad_norm": 2.5568947792053223,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 2.0525,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.03376477208778841,
652
+ "grad_norm": 2.9902150630950928,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 1.9918,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03413993622209717,
659
+ "grad_norm": 2.9363043308258057,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 1.8205,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.034515100356405926,
666
+ "grad_norm": 2.565152168273926,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 2.1421,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03489026449071469,
673
+ "grad_norm": 2.2385518550872803,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 2.1784,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03526542862502345,
680
+ "grad_norm": 2.4541680812835693,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 2.1318,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03564059275933221,
687
+ "grad_norm": 3.151038408279419,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 2.1849,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03601575689364097,
694
+ "grad_norm": 2.4328556060791016,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 2.3812,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.036390921027949726,
701
+ "grad_norm": 3.570035934448242,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 2.091,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.03676608516225849,
708
+ "grad_norm": 3.09126877784729,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 2.4002,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03714124929656725,
715
+ "grad_norm": 3.067747116088867,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 1.8106,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.03751641343087601,
722
+ "grad_norm": 5.066938400268555,
723
+ "learning_rate": 0.0,
724
+ "loss": 2.3905,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.03751641343087601,
729
+ "eval_loss": 1.49005126953125,
730
+ "eval_runtime": 366.7943,
731
+ "eval_samples_per_second": 12.241,
732
+ "eval_steps_per_second": 1.532,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.561311554001961e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null