cimol commited on
Commit
94f70e0
·
verified ·
1 Parent(s): a2941d9

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 sha256:0324b7a2b1d7bb6458a2d07b6b97a04634a6bc009c62894bc9a22cd50c63eec7
3
  size 1157746040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f82c651e066acfb676ce6604f1839c34b21b6847201e0fbed494a9f5722380
3
  size 1157746040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21ee2d5f7ce1945670e3413b4fafbae31d10210fa0fef0b8ccbab6d4367800d1
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:308424276f75cd102ec7188162807dcec81712d6a4ecaded4c3206c5ead2e25d
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b46d0b45896cd961a014025338585d94a8b5878f476cd2c3d67510d3cd41b391
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b99ec50d36f8b66e69a4933a4d39b2d9159cc8543cf6adefe72e1e6765f73f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:947b4b7e8b578cfa0f90060cb87e8d28c0e6be86b5cadcb00b9f65c8cbebcbb8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d94dee72c7d02de6c69d9fa4cc2d9dd3225f09ac52c6adcb59ec7bae1df8f10
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.8644523024559021,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.4140786749482402,
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": 6.326,
374
  "eval_steps_per_second": 1.581,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.696706304367657e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8196816444396973,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.8281573498964804,
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": 6.326,
374
  "eval_steps_per_second": 1.581,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.422360248447205,
379
+ "grad_norm": 0.3799665868282318,
380
+ "learning_rate": 6.226070475667393e-05,
381
+ "loss": 0.7939,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.4306418219461698,
386
+ "grad_norm": 0.4117141664028168,
387
+ "learning_rate": 6.189403887999006e-05,
388
+ "loss": 0.7855,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.4389233954451346,
393
+ "grad_norm": 0.4020320177078247,
394
+ "learning_rate": 6.152002044161171e-05,
395
+ "loss": 0.8022,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.4472049689440994,
400
+ "grad_norm": 0.46013712882995605,
401
+ "learning_rate": 6.113875169444539e-05,
402
+ "loss": 0.8572,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.4554865424430642,
407
+ "grad_norm": 0.45274391770362854,
408
+ "learning_rate": 6.0750336873559605e-05,
409
+ "loss": 0.7123,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.463768115942029,
414
+ "grad_norm": 0.5365428328514099,
415
+ "learning_rate": 6.035488216768811e-05,
416
+ "loss": 0.8758,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.4720496894409938,
421
+ "grad_norm": 0.641646146774292,
422
+ "learning_rate": 5.9952495690198894e-05,
423
+ "loss": 0.9564,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.4803312629399586,
428
+ "grad_norm": 0.508011519908905,
429
+ "learning_rate": 5.954328744953709e-05,
430
+ "loss": 0.8731,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.4886128364389234,
435
+ "grad_norm": 0.8867300152778625,
436
+ "learning_rate": 5.91273693191498e-05,
437
+ "loss": 0.9009,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.4968944099378882,
442
+ "grad_norm": 0.9791533946990967,
443
+ "learning_rate": 5.870485500690094e-05,
444
+ "loss": 1.1371,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.505175983436853,
449
+ "grad_norm": 0.24218077957630157,
450
+ "learning_rate": 5.827586002398468e-05,
451
+ "loss": 0.6875,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.5134575569358178,
456
+ "grad_norm": 0.22737136483192444,
457
+ "learning_rate": 5.784050165334589e-05,
458
+ "loss": 0.7116,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.5217391304347826,
463
+ "grad_norm": 0.2559671103954315,
464
+ "learning_rate": 5.739889891761608e-05,
465
+ "loss": 0.7719,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.5300207039337475,
470
+ "grad_norm": 0.24487318098545074,
471
+ "learning_rate": 5.6951172546573794e-05,
472
+ "loss": 0.7212,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.5383022774327122,
477
+ "grad_norm": 0.23421718180179596,
478
+ "learning_rate": 5.6497444944138376e-05,
479
+ "loss": 0.7471,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.546583850931677,
484
+ "grad_norm": 0.21821844577789307,
485
+ "learning_rate": 5.603784015490587e-05,
486
+ "loss": 0.6552,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.5548654244306418,
491
+ "grad_norm": 0.26210862398147583,
492
+ "learning_rate": 5.557248383023655e-05,
493
+ "loss": 0.774,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.5631469979296067,
498
+ "grad_norm": 0.2591906785964966,
499
+ "learning_rate": 5.510150319390302e-05,
500
+ "loss": 0.687,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.5714285714285714,
505
+ "grad_norm": 0.26978063583374023,
506
+ "learning_rate": 5.4625027007308546e-05,
507
+ "loss": 0.7278,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.5797101449275363,
512
+ "grad_norm": 0.24709314107894897,
513
+ "learning_rate": 5.414318553428494e-05,
514
+ "loss": 0.5976,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.587991718426501,
519
+ "grad_norm": 0.30029296875,
520
+ "learning_rate": 5.3656110505479776e-05,
521
+ "loss": 0.7129,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.5962732919254659,
526
+ "grad_norm": 0.32972994446754456,
527
+ "learning_rate": 5.316393508234253e-05,
528
+ "loss": 0.8332,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.6045548654244306,
533
+ "grad_norm": 0.3365096151828766,
534
+ "learning_rate": 5.266679382071953e-05,
535
+ "loss": 0.8121,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.6128364389233955,
540
+ "grad_norm": 0.31908273696899414,
541
+ "learning_rate": 5.216482263406778e-05,
542
+ "loss": 0.8543,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.6211180124223602,
547
+ "grad_norm": 0.3485449552536011,
548
+ "learning_rate": 5.1658158756297576e-05,
549
+ "loss": 0.8116,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.629399585921325,
554
+ "grad_norm": 0.33620256185531616,
555
+ "learning_rate": 5.114694070425407e-05,
556
+ "loss": 0.7493,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.6376811594202898,
561
+ "grad_norm": 0.35500848293304443,
562
+ "learning_rate": 5.063130823984823e-05,
563
+ "loss": 0.7026,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.6459627329192547,
568
+ "grad_norm": 0.4022809565067291,
569
+ "learning_rate": 5.011140233184724e-05,
570
+ "loss": 0.7928,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.6542443064182195,
575
+ "grad_norm": 0.41914957761764526,
576
+ "learning_rate": 4.958736511733516e-05,
577
+ "loss": 0.8219,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.6625258799171843,
582
+ "grad_norm": 0.4002333879470825,
583
+ "learning_rate": 4.905933986285393e-05,
584
+ "loss": 0.8019,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.6708074534161491,
589
+ "grad_norm": 0.46458199620246887,
590
+ "learning_rate": 4.8527470925235824e-05,
591
+ "loss": 0.7353,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.6790890269151139,
596
+ "grad_norm": 0.5049306154251099,
597
+ "learning_rate": 4.799190371213772e-05,
598
+ "loss": 0.935,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.6873706004140787,
603
+ "grad_norm": 0.48192158341407776,
604
+ "learning_rate": 4.745278464228808e-05,
605
+ "loss": 0.8568,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.6956521739130435,
610
+ "grad_norm": 0.5385396480560303,
611
+ "learning_rate": 4.69102611054575e-05,
612
+ "loss": 0.8613,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.7039337474120083,
617
+ "grad_norm": 0.4860864579677582,
618
+ "learning_rate": 4.6364481422163926e-05,
619
+ "loss": 0.8288,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.7122153209109731,
624
+ "grad_norm": 0.4691753387451172,
625
+ "learning_rate": 4.581559480312316e-05,
626
+ "loss": 0.7301,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.7204968944099379,
631
+ "grad_norm": 0.6713128685951233,
632
+ "learning_rate": 4.526375130845627e-05,
633
+ "loss": 1.0118,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.7287784679089027,
638
+ "grad_norm": 0.8337951302528381,
639
+ "learning_rate": 4.4709101806664554e-05,
640
+ "loss": 0.8735,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.7370600414078675,
645
+ "grad_norm": 0.7612811326980591,
646
+ "learning_rate": 4.4151797933383685e-05,
647
+ "loss": 0.9304,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.7453416149068323,
652
+ "grad_norm": 0.8643386960029602,
653
+ "learning_rate": 4.359199204992797e-05,
654
+ "loss": 1.0096,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.7536231884057971,
659
+ "grad_norm": 0.20685485005378723,
660
+ "learning_rate": 4.30298372016363e-05,
661
+ "loss": 0.6227,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.7619047619047619,
666
+ "grad_norm": 0.25332385301589966,
667
+ "learning_rate": 4.246548707603114e-05,
668
+ "loss": 0.7315,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.7701863354037267,
673
+ "grad_norm": 0.24437353014945984,
674
+ "learning_rate": 4.1899095960801805e-05,
675
+ "loss": 0.6921,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.7784679089026915,
680
+ "grad_norm": 0.2593900263309479,
681
+ "learning_rate": 4.133081870162385e-05,
682
+ "loss": 0.7514,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.7867494824016563,
687
+ "grad_norm": 0.2574782371520996,
688
+ "learning_rate": 4.076081065982569e-05,
689
+ "loss": 0.6447,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.7950310559006211,
694
+ "grad_norm": 0.3053584396839142,
695
+ "learning_rate": 4.018922766991447e-05,
696
+ "loss": 0.6437,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.8033126293995859,
701
+ "grad_norm": 0.2642808258533478,
702
+ "learning_rate": 3.961622599697241e-05,
703
+ "loss": 0.7539,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.8115942028985508,
708
+ "grad_norm": 0.2618858814239502,
709
+ "learning_rate": 3.9041962293935516e-05,
710
+ "loss": 0.6641,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.8198757763975155,
715
+ "grad_norm": 0.2602124512195587,
716
+ "learning_rate": 3.84665935587662e-05,
717
+ "loss": 0.6166,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.8281573498964804,
722
+ "grad_norm": 0.2887020707130432,
723
+ "learning_rate": 3.7890277091531636e-05,
724
+ "loss": 0.6502,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.8281573498964804,
729
+ "eval_loss": 0.8196816444396973,
730
+ "eval_runtime": 32.2536,
731
+ "eval_samples_per_second": 6.325,
732
+ "eval_steps_per_second": 1.581,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.373606698567598e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null