0x1202 commited on
Commit
d57ffcc
·
verified ·
1 Parent(s): 1c97530

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:c1a7cbc1c953fc782351463967dfa79a406965f3ebbf39ffb6fdc85c218f1944
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70d13c0f699e5bbd98986efd6a31c3dee651a13fe72e11b65d0c67bad468b95
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81397a08583304c5c06e14eabf5fc2714880dc66b7a837d6be395643c8ca855a
3
  size 1292176234
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55d14ec678ee693c030567f5e119f15665768fbe762580961ea782188bc0a663
3
  size 1292176234
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e84c5f2f212edc1f7aa802393ae3b1cf23dfbf6363d47b57110cc9093854c4a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b27726d4c35f32492edac7442da5b47b0931e12a036fda02a5cb60a6baa2a37
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d90116c540b4ff0066495fbccc9c914a568905fb44c6564f227952cc4231b00
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ad66011cfc1fc727a51190602a41adc332b48eeef62a5ee87c2ca9f9b90b2b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.492077499628067,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.06101281269066504,
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": 8.572,
374
  "eval_steps_per_second": 2.162,
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": 1.795134465245184e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.445011705160141,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.12202562538133008,
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": 8.572,
374
  "eval_steps_per_second": 2.162,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.06223306894447834,
379
+ "grad_norm": 1.555983543395996,
380
+ "learning_rate": 2.3816778784387097e-05,
381
+ "loss": 0.4603,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.06345332519829164,
386
+ "grad_norm": 1.726062297821045,
387
+ "learning_rate": 2.3263454721781537e-05,
388
+ "loss": 0.4604,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.06467358145210494,
393
+ "grad_norm": 1.718953013420105,
394
+ "learning_rate": 2.2693489161088592e-05,
395
+ "loss": 0.6968,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.06589383770591824,
400
+ "grad_norm": 1.4064198732376099,
401
+ "learning_rate": 2.210802993709498e-05,
402
+ "loss": 0.5862,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.06711409395973154,
407
+ "grad_norm": 1.369136095046997,
408
+ "learning_rate": 2.1508256086763372e-05,
409
+ "loss": 0.4746,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.06833435021354485,
414
+ "grad_norm": 1.502777338027954,
415
+ "learning_rate": 2.0895375474808857e-05,
416
+ "loss": 0.5513,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.06955460646735814,
421
+ "grad_norm": 1.6199352741241455,
422
+ "learning_rate": 2.0270622361220143e-05,
423
+ "loss": 0.4704,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.07077486272117145,
428
+ "grad_norm": 1.1840685606002808,
429
+ "learning_rate": 1.963525491562421e-05,
430
+ "loss": 0.3981,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.07199511897498474,
435
+ "grad_norm": 1.39909029006958,
436
+ "learning_rate": 1.8990552683500128e-05,
437
+ "loss": 0.2991,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.07321537522879805,
442
+ "grad_norm": 1.3725414276123047,
443
+ "learning_rate": 1.8337814009344716e-05,
444
+ "loss": 0.7763,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.07443563148261134,
449
+ "grad_norm": 1.4019646644592285,
450
+ "learning_rate": 1.767835342197955e-05,
451
+ "loss": 0.5279,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.07565588773642465,
456
+ "grad_norm": 1.5673801898956299,
457
+ "learning_rate": 1.7013498987264832e-05,
458
+ "loss": 0.6006,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.07687614399023796,
463
+ "grad_norm": 1.1575379371643066,
464
+ "learning_rate": 1.6344589633551502e-05,
465
+ "loss": 0.3972,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.07809640024405125,
470
+ "grad_norm": 1.2837570905685425,
471
+ "learning_rate": 1.5672972455257726e-05,
472
+ "loss": 0.5369,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.07931665649786455,
477
+ "grad_norm": 1.871349811553955,
478
+ "learning_rate": 1.5e-05,
479
+ "loss": 0.2951,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.08053691275167785,
484
+ "grad_norm": 1.4740747213363647,
485
+ "learning_rate": 1.4327027544742281e-05,
486
+ "loss": 0.7773,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.08175716900549115,
491
+ "grad_norm": 1.1336884498596191,
492
+ "learning_rate": 1.36554103664485e-05,
493
+ "loss": 0.3291,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.08297742525930446,
498
+ "grad_norm": 1.4894648790359497,
499
+ "learning_rate": 1.2986501012735174e-05,
500
+ "loss": 0.5024,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.08419768151311775,
505
+ "grad_norm": 1.3414102792739868,
506
+ "learning_rate": 1.2321646578020452e-05,
507
+ "loss": 0.4071,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.08541793776693106,
512
+ "grad_norm": 1.8325251340866089,
513
+ "learning_rate": 1.1662185990655285e-05,
514
+ "loss": 0.8575,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.08663819402074435,
519
+ "grad_norm": 1.1957671642303467,
520
+ "learning_rate": 1.1009447316499875e-05,
521
+ "loss": 0.3624,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.08785845027455766,
526
+ "grad_norm": 1.479073405265808,
527
+ "learning_rate": 1.036474508437579e-05,
528
+ "loss": 0.3765,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.08907870652837095,
533
+ "grad_norm": 1.1539698839187622,
534
+ "learning_rate": 9.729377638779859e-06,
535
+ "loss": 0.318,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.09029896278218426,
540
+ "grad_norm": 1.653338074684143,
541
+ "learning_rate": 9.104624525191147e-06,
542
+ "loss": 0.3384,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.09151921903599756,
547
+ "grad_norm": 1.7880301475524902,
548
+ "learning_rate": 8.491743913236629e-06,
549
+ "loss": 0.7647,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.09273947528981086,
554
+ "grad_norm": 1.749808669090271,
555
+ "learning_rate": 7.89197006290502e-06,
556
+ "loss": 0.727,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.09395973154362416,
561
+ "grad_norm": 1.8830204010009766,
562
+ "learning_rate": 7.30651083891141e-06,
563
+ "loss": 0.6698,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.09517998779743746,
568
+ "grad_norm": 2.900890588760376,
569
+ "learning_rate": 6.736545278218464e-06,
570
+ "loss": 0.2807,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.09640024405125076,
575
+ "grad_norm": 2.5810508728027344,
576
+ "learning_rate": 6.1832212156129045e-06,
577
+ "loss": 0.5424,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.09762050030506407,
582
+ "grad_norm": 1.8283663988113403,
583
+ "learning_rate": 5.647652972118998e-06,
584
+ "loss": 0.7818,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.09884075655887736,
589
+ "grad_norm": 2.1838881969451904,
590
+ "learning_rate": 5.130919110904311e-06,
591
+ "loss": 0.5499,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.10006101281269067,
596
+ "grad_norm": 2.056957960128784,
597
+ "learning_rate": 4.6340602651970304e-06,
598
+ "loss": 0.6527,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.10128126906650396,
603
+ "grad_norm": 1.682894229888916,
604
+ "learning_rate": 4.158077042589129e-06,
605
+ "loss": 0.3389,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.10250152532031727,
610
+ "grad_norm": 1.9048279523849487,
611
+ "learning_rate": 3.7039280099458373e-06,
612
+ "loss": 0.5434,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.10372178157413056,
617
+ "grad_norm": 1.9600788354873657,
618
+ "learning_rate": 3.272527762979553e-06,
619
+ "loss": 0.4242,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.10494203782794387,
624
+ "grad_norm": 2.029824733734131,
625
+ "learning_rate": 2.86474508437579e-06,
626
+ "loss": 0.754,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.10616229408175717,
631
+ "grad_norm": 1.647495150566101,
632
+ "learning_rate": 2.4814011941804603e-06,
633
+ "loss": 0.2308,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.10738255033557047,
638
+ "grad_norm": 2.4339029788970947,
639
+ "learning_rate": 2.1232680959720085e-06,
640
+ "loss": 0.6364,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.10860280658938377,
645
+ "grad_norm": 3.1728689670562744,
646
+ "learning_rate": 1.79106702214893e-06,
647
+ "loss": 0.3479,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.10982306284319707,
652
+ "grad_norm": 1.8751670122146606,
653
+ "learning_rate": 1.4854669814637145e-06,
654
+ "loss": 0.2656,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.11104331909701037,
659
+ "grad_norm": 1.807173252105713,
660
+ "learning_rate": 1.2070834117282414e-06,
661
+ "loss": 0.1919,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.11226357535082367,
666
+ "grad_norm": 3.3415565490722656,
667
+ "learning_rate": 9.56476940403942e-07,
668
+ "loss": 0.2879,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.11348383160463697,
673
+ "grad_norm": 6.014771938323975,
674
+ "learning_rate": 7.341522555726971e-07,
675
+ "loss": 0.486,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.11470408785845028,
680
+ "grad_norm": 1.8159458637237549,
681
+ "learning_rate": 5.405570895622014e-07,
682
+ "loss": 0.6534,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.11592434411226357,
687
+ "grad_norm": 2.759377956390381,
688
+ "learning_rate": 3.760813172726457e-07,
689
+ "loss": 0.3343,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.11714460036607688,
694
+ "grad_norm": 2.1716294288635254,
695
+ "learning_rate": 2.41056171020555e-07,
696
+ "loss": 0.2218,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.11836485661989017,
701
+ "grad_norm": 3.249907970428467,
702
+ "learning_rate": 1.357535734809795e-07,
703
+ "loss": 0.3062,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.11958511287370348,
708
+ "grad_norm": 3.0555734634399414,
709
+ "learning_rate": 6.038559007141397e-08,
710
+ "loss": 0.2289,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.12080536912751678,
715
+ "grad_norm": 5.055708408355713,
716
+ "learning_rate": 1.510400188028116e-08,
717
+ "loss": 0.2759,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.12202562538133008,
722
+ "grad_norm": 7.7404255867004395,
723
+ "learning_rate": 0.0,
724
+ "loss": 0.5774,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.12202562538133008,
729
+ "eval_loss": 0.445011705160141,
730
+ "eval_runtime": 40.2119,
731
+ "eval_samples_per_second": 8.58,
732
+ "eval_steps_per_second": 2.164,
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": 3.572495321923584e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null