lesso commited on
Commit
ce1aaf1
·
verified ·
1 Parent(s): 37014fe

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 sha256:0d524bf2136781d5528f5aea3d8a01e798e36c0d2ba4d0ebc35ce212e823cff9
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a390ab90c983b502232f6dd978c1d10bd073cbd71369a7a0c14a61fba37ebca
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88d23e730fb275105225fd43ccdf2f6b04de210bae8980989fba0545af4c033c
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4b3bc4c954ea220c7ba8aecc83e5b5ceea33371e9415d87cb5ab5603a4f2566
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd6b7d0b5bd3ebe3fb5a1d6ddd6a28facb1cf25d5362c637a7af23ee92e8ab4d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25b5f3b462fb3e29221ae0588e7591e3e9adfa54f981e07b5869f484f6b0ecc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcbe1ba74b58330afa49026b3467516d09bde409f813ca3b749b16b9edb36df4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab3d2b0401484126213dd055d9044edf00d7b06db4fe9dbad6027ee8b5d34b1
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8269708752632141,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0023223409196470044,
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": 55.688,
374
  "eval_steps_per_second": 13.925,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3119728734240768.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7575440406799316,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.004644681839294009,
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": 55.688,
374
  "eval_steps_per_second": 13.925,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.002368787738039944,
379
+ "grad_norm": 2.7304725646972656,
380
+ "learning_rate": 7.983263157894736e-05,
381
+ "loss": 0.7953,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.002415234556432884,
386
+ "grad_norm": 2.282052516937256,
387
+ "learning_rate": 7.929684210526315e-05,
388
+ "loss": 0.8493,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0024616813748258243,
393
+ "grad_norm": 2.524898052215576,
394
+ "learning_rate": 7.876105263157895e-05,
395
+ "loss": 1.0108,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.0025081281932187644,
400
+ "grad_norm": 2.6745500564575195,
401
+ "learning_rate": 7.822526315789473e-05,
402
+ "loss": 1.0531,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0025545750116117046,
407
+ "grad_norm": 3.1213998794555664,
408
+ "learning_rate": 7.768947368421053e-05,
409
+ "loss": 1.1068,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0026010218300046447,
414
+ "grad_norm": 3.499636173248291,
415
+ "learning_rate": 7.715368421052631e-05,
416
+ "loss": 1.0808,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.002647468648397585,
421
+ "grad_norm": 3.125180721282959,
422
+ "learning_rate": 7.66178947368421e-05,
423
+ "loss": 0.8485,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.002693915466790525,
428
+ "grad_norm": 2.547490119934082,
429
+ "learning_rate": 7.608210526315788e-05,
430
+ "loss": 0.7604,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.002740362285183465,
435
+ "grad_norm": 2.058576822280884,
436
+ "learning_rate": 7.554631578947368e-05,
437
+ "loss": 0.665,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.002786809103576405,
442
+ "grad_norm": 2.624077320098877,
443
+ "learning_rate": 7.501052631578947e-05,
444
+ "loss": 0.6822,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0028332559219693453,
449
+ "grad_norm": 1.4456878900527954,
450
+ "learning_rate": 7.447473684210527e-05,
451
+ "loss": 0.554,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.002879702740362285,
456
+ "grad_norm": 1.9477028846740723,
457
+ "learning_rate": 7.393894736842105e-05,
458
+ "loss": 0.712,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.002926149558755225,
463
+ "grad_norm": 2.0057406425476074,
464
+ "learning_rate": 7.340315789473684e-05,
465
+ "loss": 0.7368,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0029725963771481652,
470
+ "grad_norm": 2.041309356689453,
471
+ "learning_rate": 7.286736842105262e-05,
472
+ "loss": 0.9478,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.0030190431955411053,
477
+ "grad_norm": 1.8585742712020874,
478
+ "learning_rate": 7.233157894736842e-05,
479
+ "loss": 0.5883,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0030654900139340455,
484
+ "grad_norm": 2.3726940155029297,
485
+ "learning_rate": 7.179578947368421e-05,
486
+ "loss": 0.8448,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0031119368323269856,
491
+ "grad_norm": 4.274697303771973,
492
+ "learning_rate": 7.125999999999999e-05,
493
+ "loss": 0.693,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.0031583836507199257,
498
+ "grad_norm": 1.7456036806106567,
499
+ "learning_rate": 7.072421052631579e-05,
500
+ "loss": 0.6139,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.003204830469112866,
505
+ "grad_norm": 2.077462673187256,
506
+ "learning_rate": 7.018842105263158e-05,
507
+ "loss": 0.6687,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.003251277287505806,
512
+ "grad_norm": 1.6591328382492065,
513
+ "learning_rate": 6.965263157894736e-05,
514
+ "loss": 0.6602,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.003297724105898746,
519
+ "grad_norm": 2.040104866027832,
520
+ "learning_rate": 6.911684210526316e-05,
521
+ "loss": 0.6718,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.003344170924291686,
526
+ "grad_norm": 2.031517505645752,
527
+ "learning_rate": 6.858105263157894e-05,
528
+ "loss": 0.6965,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.003390617742684626,
533
+ "grad_norm": 1.677396297454834,
534
+ "learning_rate": 6.804526315789473e-05,
535
+ "loss": 0.6022,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.003437064561077566,
540
+ "grad_norm": 2.6971142292022705,
541
+ "learning_rate": 6.750947368421052e-05,
542
+ "loss": 0.7803,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.003483511379470506,
547
+ "grad_norm": 1.2442923784255981,
548
+ "learning_rate": 6.697368421052631e-05,
549
+ "loss": 0.4904,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0035299581978634463,
554
+ "grad_norm": 1.520882487297058,
555
+ "learning_rate": 6.64378947368421e-05,
556
+ "loss": 0.5449,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.0035764050162563864,
561
+ "grad_norm": 2.945136070251465,
562
+ "learning_rate": 6.59021052631579e-05,
563
+ "loss": 0.5945,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0036228518346493265,
568
+ "grad_norm": 2.225796937942505,
569
+ "learning_rate": 6.536631578947368e-05,
570
+ "loss": 0.8414,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.0036692986530422666,
575
+ "grad_norm": 3.5419042110443115,
576
+ "learning_rate": 6.483052631578947e-05,
577
+ "loss": 0.951,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0037157454714352067,
582
+ "grad_norm": 2.4470789432525635,
583
+ "learning_rate": 6.429473684210525e-05,
584
+ "loss": 0.6766,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.003762192289828147,
589
+ "grad_norm": 1.8150739669799805,
590
+ "learning_rate": 6.375894736842104e-05,
591
+ "loss": 0.6212,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.003808639108221087,
596
+ "grad_norm": 2.2378828525543213,
597
+ "learning_rate": 6.322315789473684e-05,
598
+ "loss": 0.912,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.003855085926614027,
603
+ "grad_norm": 2.66448974609375,
604
+ "learning_rate": 6.268736842105264e-05,
605
+ "loss": 0.7284,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0039015327450069672,
610
+ "grad_norm": 2.0171289443969727,
611
+ "learning_rate": 6.215157894736842e-05,
612
+ "loss": 0.5339,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.003947979563399907,
617
+ "grad_norm": 1.829827070236206,
618
+ "learning_rate": 6.16157894736842e-05,
619
+ "loss": 0.6982,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.003994426381792847,
624
+ "grad_norm": 1.3786966800689697,
625
+ "learning_rate": 6.107999999999999e-05,
626
+ "loss": 0.4433,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.004040873200185788,
631
+ "grad_norm": 2.0562403202056885,
632
+ "learning_rate": 6.054421052631578e-05,
633
+ "loss": 0.791,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.004087320018578727,
638
+ "grad_norm": 1.8710417747497559,
639
+ "learning_rate": 6.000842105263157e-05,
640
+ "loss": 0.5487,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.004133766836971668,
645
+ "grad_norm": 2.46244215965271,
646
+ "learning_rate": 5.947263157894737e-05,
647
+ "loss": 0.9045,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0041802136553646075,
652
+ "grad_norm": 1.9283982515335083,
653
+ "learning_rate": 5.893684210526316e-05,
654
+ "loss": 0.6472,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.004226660473757547,
659
+ "grad_norm": 1.794073462486267,
660
+ "learning_rate": 5.8401052631578944e-05,
661
+ "loss": 0.7332,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.004273107292150488,
666
+ "grad_norm": 2.4211764335632324,
667
+ "learning_rate": 5.7865263157894736e-05,
668
+ "loss": 0.9175,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0043195541105434275,
673
+ "grad_norm": 2.131087064743042,
674
+ "learning_rate": 5.732947368421052e-05,
675
+ "loss": 0.846,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.004366000928936368,
680
+ "grad_norm": 3.606595993041992,
681
+ "learning_rate": 5.6793684210526306e-05,
682
+ "loss": 1.023,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.004412447747329308,
687
+ "grad_norm": 2.0817458629608154,
688
+ "learning_rate": 5.6257894736842105e-05,
689
+ "loss": 0.7585,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.004458894565722248,
694
+ "grad_norm": 2.736661672592163,
695
+ "learning_rate": 5.57221052631579e-05,
696
+ "loss": 0.9443,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.004505341384115188,
701
+ "grad_norm": 1.7814656496047974,
702
+ "learning_rate": 5.518631578947368e-05,
703
+ "loss": 0.9056,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0045517882025081285,
708
+ "grad_norm": 2.098845958709717,
709
+ "learning_rate": 5.4650526315789474e-05,
710
+ "loss": 0.7014,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.004598235020901068,
715
+ "grad_norm": 2.316159963607788,
716
+ "learning_rate": 5.411473684210526e-05,
717
+ "loss": 0.7147,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.004644681839294009,
722
+ "grad_norm": 2.182925224304199,
723
+ "learning_rate": 5.3578947368421044e-05,
724
+ "loss": 0.7637,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.004644681839294009,
729
+ "eval_loss": 0.7575440406799316,
730
+ "eval_runtime": 162.5731,
731
+ "eval_samples_per_second": 55.766,
732
+ "eval_steps_per_second": 13.944,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6106135727702016.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null