nttx commited on
Commit
ed19125
·
verified ·
1 Parent(s): 03e294b

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 sha256:2700b510245a093ed4ef3f79ede57abd0ab802819639f825fa166657c575b042
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e7a099847dea4dd277efcb63019da72f71a60fab0f71ea763f415d31e79a49
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b966f2b1b67a9f1365c69160352e75f6b095cae0878878c5697addd44a4aa3a
3
  size 101184122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37402fde3ce10e12747101fd1c72c8e72a0f61e23a7b13e837aa24762e118c5d
3
  size 101184122
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a592212b90b5a9587cd0c392ec18153618ed953c33f9fb6a99da1238550d7ddd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efeda52182c55d20997af5f8c339baddc44ac392edfb6d210ffa2309ed79b90b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4286912679672241,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0033558173093056814,
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": 46.744,
374
  "eval_steps_per_second": 11.687,
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": 5146843860172800.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1696587800979614,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.006711634618611363,
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": 46.744,
374
  "eval_steps_per_second": 11.687,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.003422933655491795,
379
+ "grad_norm": 8.607892990112305,
380
+ "learning_rate": 5.695865504800327e-05,
381
+ "loss": 1.3872,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.003490050001677909,
386
+ "grad_norm": 7.4620184898376465,
387
+ "learning_rate": 5.522642316338268e-05,
388
+ "loss": 1.8064,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0035571663478640224,
393
+ "grad_norm": 10.338674545288086,
394
+ "learning_rate": 5.348782368720626e-05,
395
+ "loss": 1.9793,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.003624282694050136,
400
+ "grad_norm": 5.747066497802734,
401
+ "learning_rate": 5.174497483512506e-05,
402
+ "loss": 1.2235,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0036913990402362494,
407
+ "grad_norm": 3.031548261642456,
408
+ "learning_rate": 5e-05,
409
+ "loss": 0.8986,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0037585153864223633,
414
+ "grad_norm": 4.52862548828125,
415
+ "learning_rate": 4.825502516487497e-05,
416
+ "loss": 1.1097,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.003825631732608477,
421
+ "grad_norm": 5.04213285446167,
422
+ "learning_rate": 4.6512176312793736e-05,
423
+ "loss": 1.4255,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0038927480787945903,
428
+ "grad_norm": 7.351133346557617,
429
+ "learning_rate": 4.477357683661734e-05,
430
+ "loss": 1.1968,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.003959864424980704,
435
+ "grad_norm": 9.476580619812012,
436
+ "learning_rate": 4.3041344951996746e-05,
437
+ "loss": 1.3291,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.004026980771166817,
442
+ "grad_norm": 3.8244152069091797,
443
+ "learning_rate": 4.131759111665349e-05,
444
+ "loss": 1.0277,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.004094097117352932,
449
+ "grad_norm": 5.939021587371826,
450
+ "learning_rate": 3.960441545911204e-05,
451
+ "loss": 0.9494,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.004161213463539045,
456
+ "grad_norm": 8.482564926147461,
457
+ "learning_rate": 3.790390522001662e-05,
458
+ "loss": 1.8094,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.004228329809725159,
463
+ "grad_norm": 12.220017433166504,
464
+ "learning_rate": 3.6218132209150045e-05,
465
+ "loss": 1.9515,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.004295446155911272,
470
+ "grad_norm": 9.194010734558105,
471
+ "learning_rate": 3.4549150281252636e-05,
472
+ "loss": 2.0774,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.004362562502097386,
477
+ "grad_norm": 4.340768337249756,
478
+ "learning_rate": 3.289899283371657e-05,
479
+ "loss": 1.0,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.004429678848283499,
484
+ "grad_norm": 4.69960355758667,
485
+ "learning_rate": 3.12696703292044e-05,
486
+ "loss": 1.202,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.004496795194469613,
491
+ "grad_norm": 3.9642746448516846,
492
+ "learning_rate": 2.9663167846209998e-05,
493
+ "loss": 1.1606,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.004563911540655726,
498
+ "grad_norm": 4.475998878479004,
499
+ "learning_rate": 2.8081442660546125e-05,
500
+ "loss": 1.1735,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.004631027886841841,
505
+ "grad_norm": 5.146561145782471,
506
+ "learning_rate": 2.6526421860705473e-05,
507
+ "loss": 1.0892,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.004698144233027954,
512
+ "grad_norm": 7.040509223937988,
513
+ "learning_rate": 2.500000000000001e-05,
514
+ "loss": 0.9862,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.004765260579214068,
519
+ "grad_norm": 15.23552131652832,
520
+ "learning_rate": 2.350403678833976e-05,
521
+ "loss": 1.3052,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.004832376925400181,
526
+ "grad_norm": 8.604045867919922,
527
+ "learning_rate": 2.2040354826462668e-05,
528
+ "loss": 1.5791,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.004899493271586295,
533
+ "grad_norm": 6.7834014892578125,
534
+ "learning_rate": 2.061073738537635e-05,
535
+ "loss": 1.494,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.004966609617772408,
540
+ "grad_norm": 2.922942638397217,
541
+ "learning_rate": 1.9216926233717085e-05,
542
+ "loss": 0.8164,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.005033725963958522,
547
+ "grad_norm": 3.52816104888916,
548
+ "learning_rate": 1.7860619515673033e-05,
549
+ "loss": 0.7509,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.005100842310144636,
554
+ "grad_norm": 9.099770545959473,
555
+ "learning_rate": 1.6543469682057106e-05,
556
+ "loss": 1.6448,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.00516795865633075,
561
+ "grad_norm": 6.2389936447143555,
562
+ "learning_rate": 1.526708147705013e-05,
563
+ "loss": 1.299,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.005235075002516863,
568
+ "grad_norm": 7.375805854797363,
569
+ "learning_rate": 1.4033009983067452e-05,
570
+ "loss": 1.1563,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.005302191348702977,
575
+ "grad_norm": 9.736416816711426,
576
+ "learning_rate": 1.2842758726130283e-05,
577
+ "loss": 1.0908,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.00536930769488909,
582
+ "grad_norm": 3.867943048477173,
583
+ "learning_rate": 1.1697777844051105e-05,
584
+ "loss": 0.7306,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.005436424041075204,
589
+ "grad_norm": 10.5623197555542,
590
+ "learning_rate": 1.0599462319663905e-05,
591
+ "loss": 1.8625,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.005503540387261317,
596
+ "grad_norm": 5.438706874847412,
597
+ "learning_rate": 9.549150281252633e-06,
598
+ "loss": 1.3818,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0055706567334474315,
603
+ "grad_norm": 4.647777557373047,
604
+ "learning_rate": 8.548121372247918e-06,
605
+ "loss": 1.0517,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.005637773079633545,
610
+ "grad_norm": 7.829025745391846,
611
+ "learning_rate": 7.597595192178702e-06,
612
+ "loss": 1.2179,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.0057048894258196585,
617
+ "grad_norm": 16.5595760345459,
618
+ "learning_rate": 6.698729810778065e-06,
619
+ "loss": 1.7391,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.005772005772005772,
624
+ "grad_norm": 6.000573635101318,
625
+ "learning_rate": 5.852620357053651e-06,
626
+ "loss": 1.6609,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.0058391221181918855,
631
+ "grad_norm": 4.75664758682251,
632
+ "learning_rate": 5.060297685041659e-06,
633
+ "loss": 1.2606,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.005906238464377999,
638
+ "grad_norm": 4.944088459014893,
639
+ "learning_rate": 4.322727117869951e-06,
640
+ "loss": 1.254,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.0059733548105641125,
645
+ "grad_norm": 5.672614574432373,
646
+ "learning_rate": 3.6408072716606346e-06,
647
+ "loss": 1.4045,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.006040471156750227,
652
+ "grad_norm": 5.398680210113525,
653
+ "learning_rate": 3.0153689607045845e-06,
654
+ "loss": 1.2013,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.00610758750293634,
659
+ "grad_norm": 5.356427192687988,
660
+ "learning_rate": 2.4471741852423237e-06,
661
+ "loss": 1.1558,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.006174703849122454,
666
+ "grad_norm": 3.6810734272003174,
667
+ "learning_rate": 1.9369152030840556e-06,
668
+ "loss": 1.1569,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.006241820195308567,
673
+ "grad_norm": 5.677954196929932,
674
+ "learning_rate": 1.4852136862001764e-06,
675
+ "loss": 1.2686,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.006308936541494681,
680
+ "grad_norm": 5.77936315536499,
681
+ "learning_rate": 1.0926199633097157e-06,
682
+ "loss": 1.5107,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.006376052887680794,
687
+ "grad_norm": 9.271018028259277,
688
+ "learning_rate": 7.596123493895991e-07,
689
+ "loss": 1.2887,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.006443169233866908,
694
+ "grad_norm": 3.8657755851745605,
695
+ "learning_rate": 4.865965629214819e-07,
696
+ "loss": 1.0361,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.006510285580053022,
701
+ "grad_norm": 5.270502090454102,
702
+ "learning_rate": 2.7390523158633554e-07,
703
+ "loss": 1.2172,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.006577401926239136,
708
+ "grad_norm": 7.928878307342529,
709
+ "learning_rate": 1.2179748700879012e-07,
710
+ "loss": 2.0708,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.006644518272425249,
715
+ "grad_norm": 6.460588455200195,
716
+ "learning_rate": 3.04586490452119e-08,
717
+ "loss": 1.6989,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.006711634618611363,
722
+ "grad_norm": 10.74853801727295,
723
+ "learning_rate": 0.0,
724
+ "loss": 1.8404,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.006711634618611363,
729
+ "eval_loss": 1.1696587800979614,
730
+ "eval_runtime": 268.5872,
731
+ "eval_samples_per_second": 46.715,
732
+ "eval_steps_per_second": 11.68,
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": 1.02936877203456e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null