bbytxt commited on
Commit
3a95359
·
verified ·
1 Parent(s): 28b4102

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 sha256:02edc4b02f62d109a35534f11253a324c6257b8b53069aeb8a8d49a0b6142d89
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:411f23acc11146e6760198e69dd38a6c64eef7907fe30a866d8041e4eaa91e91
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abb6e481daac2ad419abf36701f170e306ea7516ba2deb075a33e70de29b6c41
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c127e5c23dbe84e1ea95179aaba6d299a9f3f8de0f354fcb5cb0f312d701236
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24bcb0ec76c9f2798cf88100af6502beaa914ce76bf36fa00fa354522e95d48c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c2a303531872d65021a22b95bc0b62a861072952edcb2386cfbc73501e1974
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21bca0277a807518b292d79cbef83cbf0fd2afc472e011178f03e012f40013f9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c35f928f7dd9edebe7c94dc66def3d207bbcfc6fb428fd758a6bfcafaf8bae8
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.4165593981742859,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.8733624454148472,
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": 33.219,
374
  "eval_steps_per_second": 8.562,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.381134508228608e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.16824179887771606,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.7467248908296944,
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": 33.219,
374
  "eval_steps_per_second": 8.562,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.8908296943231441,
379
+ "grad_norm": 1.121232271194458,
380
+ "learning_rate": 8.501086738835843e-05,
381
+ "loss": 0.3865,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.9082969432314411,
386
+ "grad_norm": 1.3548880815505981,
387
+ "learning_rate": 8.43120818934367e-05,
388
+ "loss": 0.493,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.925764192139738,
393
+ "grad_norm": 1.6399530172348022,
394
+ "learning_rate": 8.360039302777612e-05,
395
+ "loss": 0.4454,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.9432314410480349,
400
+ "grad_norm": 2.1539204120635986,
401
+ "learning_rate": 8.28760684284532e-05,
402
+ "loss": 0.5806,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.9606986899563319,
407
+ "grad_norm": 1.3799574375152588,
408
+ "learning_rate": 8.213938048432697e-05,
409
+ "loss": 0.3791,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.9781659388646288,
414
+ "grad_norm": 1.6386706829071045,
415
+ "learning_rate": 8.139060623360493e-05,
416
+ "loss": 0.3788,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.9956331877729258,
421
+ "grad_norm": 1.8362394571304321,
422
+ "learning_rate": 8.063002725966015e-05,
423
+ "loss": 0.3617,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.0131004366812226,
428
+ "grad_norm": 4.955390453338623,
429
+ "learning_rate": 7.985792958513931e-05,
430
+ "loss": 0.7963,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.0305676855895196,
435
+ "grad_norm": 1.039722204208374,
436
+ "learning_rate": 7.907460356440133e-05,
437
+ "loss": 0.2566,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.0480349344978166,
442
+ "grad_norm": 0.9322420358657837,
443
+ "learning_rate": 7.828034377432693e-05,
444
+ "loss": 0.3009,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.0655021834061136,
449
+ "grad_norm": 1.1808615922927856,
450
+ "learning_rate": 7.74754489035403e-05,
451
+ "loss": 0.3358,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.0829694323144106,
456
+ "grad_norm": 0.9506165981292725,
457
+ "learning_rate": 7.666022164008457e-05,
458
+ "loss": 0.2231,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.1004366812227073,
463
+ "grad_norm": 1.2802693843841553,
464
+ "learning_rate": 7.583496855759316e-05,
465
+ "loss": 0.2601,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.1179039301310043,
470
+ "grad_norm": 1.6419092416763306,
471
+ "learning_rate": 7.500000000000001e-05,
472
+ "loss": 0.2622,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.1353711790393013,
477
+ "grad_norm": 0.9867280125617981,
478
+ "learning_rate": 7.415562996483192e-05,
479
+ "loss": 0.2306,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.1528384279475983,
484
+ "grad_norm": 1.1051852703094482,
485
+ "learning_rate": 7.330217598512695e-05,
486
+ "loss": 0.2497,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.1703056768558953,
491
+ "grad_norm": 1.6345847845077515,
492
+ "learning_rate": 7.243995901002312e-05,
493
+ "loss": 0.2628,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.1877729257641922,
498
+ "grad_norm": 1.4212472438812256,
499
+ "learning_rate": 7.156930328406268e-05,
500
+ "loss": 0.2629,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.205240174672489,
505
+ "grad_norm": 1.264844536781311,
506
+ "learning_rate": 7.069053622525696e-05,
507
+ "loss": 0.2389,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.222707423580786,
512
+ "grad_norm": 1.098765254020691,
513
+ "learning_rate": 6.980398830195785e-05,
514
+ "loss": 0.1724,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.240174672489083,
519
+ "grad_norm": 4.439842224121094,
520
+ "learning_rate": 6.890999290858214e-05,
521
+ "loss": 0.3221,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.25764192139738,
526
+ "grad_norm": 1.4293755292892456,
527
+ "learning_rate": 6.800888624023553e-05,
528
+ "loss": 0.2996,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.2751091703056767,
533
+ "grad_norm": 1.592860460281372,
534
+ "learning_rate": 6.710100716628344e-05,
535
+ "loss": 0.2456,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.2925764192139737,
540
+ "grad_norm": 1.2025070190429688,
541
+ "learning_rate": 6.618669710291606e-05,
542
+ "loss": 0.2663,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.3100436681222707,
547
+ "grad_norm": 0.9999786019325256,
548
+ "learning_rate": 6.526629988475567e-05,
549
+ "loss": 0.2102,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.3275109170305677,
554
+ "grad_norm": 1.3882269859313965,
555
+ "learning_rate": 6.434016163555452e-05,
556
+ "loss": 0.1725,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.3449781659388647,
561
+ "grad_norm": 1.0446701049804688,
562
+ "learning_rate": 6.340863063803188e-05,
563
+ "loss": 0.1511,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.3624454148471616,
568
+ "grad_norm": 1.5679444074630737,
569
+ "learning_rate": 6.247205720289907e-05,
570
+ "loss": 0.217,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.3799126637554586,
575
+ "grad_norm": 1.159275770187378,
576
+ "learning_rate": 6.153079353712201e-05,
577
+ "loss": 0.142,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.3973799126637554,
582
+ "grad_norm": 1.1023359298706055,
583
+ "learning_rate": 6.058519361147055e-05,
584
+ "loss": 0.1504,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.4148471615720524,
589
+ "grad_norm": 1.6043438911437988,
590
+ "learning_rate": 5.963561302740449e-05,
591
+ "loss": 0.1497,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.4323144104803494,
596
+ "grad_norm": 1.2015390396118164,
597
+ "learning_rate": 5.868240888334653e-05,
598
+ "loss": 0.2159,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.4497816593886463,
603
+ "grad_norm": 1.9150855541229248,
604
+ "learning_rate": 5.772593964039203e-05,
605
+ "loss": 0.2409,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.467248908296943,
610
+ "grad_norm": 1.2557482719421387,
611
+ "learning_rate": 5.6766564987506566e-05,
612
+ "loss": 0.1594,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.48471615720524,
617
+ "grad_norm": 3.442033052444458,
618
+ "learning_rate": 5.5804645706261514e-05,
619
+ "loss": 0.1946,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.502183406113537,
624
+ "grad_norm": 1.3177473545074463,
625
+ "learning_rate": 5.484054353515896e-05,
626
+ "loss": 0.3011,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.519650655021834,
631
+ "grad_norm": 0.811776340007782,
632
+ "learning_rate": 5.387462103359655e-05,
633
+ "loss": 0.1271,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.537117903930131,
638
+ "grad_norm": 1.0938807725906372,
639
+ "learning_rate": 5.290724144552379e-05,
640
+ "loss": 0.1645,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.554585152838428,
645
+ "grad_norm": 0.7474001049995422,
646
+ "learning_rate": 5.193876856284085e-05,
647
+ "loss": 0.1091,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.572052401746725,
652
+ "grad_norm": 1.4519085884094238,
653
+ "learning_rate": 5.096956658859122e-05,
654
+ "loss": 0.2083,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.589519650655022,
659
+ "grad_norm": 1.1171748638153076,
660
+ "learning_rate": 5e-05,
661
+ "loss": 0.1567,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.6069868995633187,
666
+ "grad_norm": 1.226719856262207,
667
+ "learning_rate": 4.903043341140879e-05,
668
+ "loss": 0.1468,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.6244541484716157,
673
+ "grad_norm": 1.6665370464324951,
674
+ "learning_rate": 4.806123143715916e-05,
675
+ "loss": 0.215,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.6419213973799127,
680
+ "grad_norm": 1.3081082105636597,
681
+ "learning_rate": 4.709275855447621e-05,
682
+ "loss": 0.1094,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.6593886462882095,
687
+ "grad_norm": 1.3947356939315796,
688
+ "learning_rate": 4.612537896640346e-05,
689
+ "loss": 0.1714,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.6768558951965065,
694
+ "grad_norm": 1.4104937314987183,
695
+ "learning_rate": 4.515945646484105e-05,
696
+ "loss": 0.1227,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.6943231441048034,
701
+ "grad_norm": 1.774125337600708,
702
+ "learning_rate": 4.4195354293738484e-05,
703
+ "loss": 0.152,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.7117903930131004,
708
+ "grad_norm": 2.2607905864715576,
709
+ "learning_rate": 4.323343501249346e-05,
710
+ "loss": 0.0859,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.7292576419213974,
715
+ "grad_norm": 1.8278192281723022,
716
+ "learning_rate": 4.227406035960798e-05,
717
+ "loss": 0.1364,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.7467248908296944,
722
+ "grad_norm": 1.3324322700500488,
723
+ "learning_rate": 4.131759111665349e-05,
724
+ "loss": 0.2195,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.7467248908296944,
729
+ "eval_loss": 0.16824179887771606,
730
+ "eval_runtime": 2.9465,
731
+ "eval_samples_per_second": 32.921,
732
+ "eval_steps_per_second": 8.485,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.758016755040256e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null