nttx commited on
Commit
07e72ce
·
verified ·
1 Parent(s): 7d92e74

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 sha256:789736b12870a73e69dcf2ef9bdba0e500e7575487bb5e00ad5e34e7ba987fae
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2794f115ecf7647a6de9adb317856a63e77984749639ba97d9cbdf91bc87aca7
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:276f7135f717a4597caf6c767a8cfeab22e479d20e66370f41461920e037208e
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21eaece1b7a8f0a0542a82464eea7d5251f50c5b2e80831d82b267bd806b0b66
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7eeb7b51f69aaa9cc0526b77cf6310b6cc11c0afd67201a6b54c1dfed577428
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a051c9e2f2c55a5c851b2f1a78d680e9c7c3cc8e39cb52088d27e52c1c3fcec
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f5b4ba066d00b62be68b9f9ec9376def1ffea9a45f98d620f3198033186a6a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6253278255462646,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.04927322000492732,
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": 10.674,
374
  "eval_steps_per_second": 5.34,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 8.560814559382733e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6039547920227051,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.09854644000985464,
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": 10.674,
374
  "eval_steps_per_second": 5.34,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.05025868440502587,
379
+ "grad_norm": 0.09365927428007126,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 0.0552,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.051244148805124415,
386
+ "grad_norm": 0.13093718886375427,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 0.1879,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.052229613205222965,
393
+ "grad_norm": 0.17437294125556946,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 0.23,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.05321507760532151,
400
+ "grad_norm": 0.2906794250011444,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 0.3665,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.05420054200542006,
407
+ "grad_norm": 0.2222241759300232,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 0.4059,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0551860064055186,
414
+ "grad_norm": 0.24162358045578003,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 0.5642,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.05617147080561715,
421
+ "grad_norm": 0.21459117531776428,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 0.6121,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.057156935205715693,
428
+ "grad_norm": 0.2023555487394333,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 0.5059,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.05814239960581424,
435
+ "grad_norm": 0.2224394828081131,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 0.6517,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.059127864005912786,
442
+ "grad_norm": 0.24458082020282745,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 0.7442,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.060113328406011336,
449
+ "grad_norm": 0.22274242341518402,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 0.6335,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.06109879280610988,
456
+ "grad_norm": 0.2185131013393402,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 0.5323,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.06208425720620843,
463
+ "grad_norm": 0.21939384937286377,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 0.6066,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.06306972160630697,
470
+ "grad_norm": 0.20755380392074585,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 0.5819,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.06405518600640552,
477
+ "grad_norm": 0.2545813024044037,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 0.7208,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.06504065040650407,
484
+ "grad_norm": 0.25121399760246277,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 0.8203,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.06602611480660261,
491
+ "grad_norm": 0.23934347927570343,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 0.6853,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.06701157920670116,
498
+ "grad_norm": 0.2448682188987732,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 0.8493,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.0679970436067997,
505
+ "grad_norm": 0.21752771735191345,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 0.4707,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.06898250800689826,
512
+ "grad_norm": 0.2293497771024704,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 0.6304,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.0699679724069968,
519
+ "grad_norm": 0.24045786261558533,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 0.6314,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.07095343680709534,
526
+ "grad_norm": 0.26281052827835083,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 0.619,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.07193890120719389,
533
+ "grad_norm": 0.28175660967826843,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 0.7979,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.07292436560729244,
540
+ "grad_norm": 0.2699892520904541,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 0.7732,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.07390983000739099,
547
+ "grad_norm": 0.2922893166542053,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 0.8827,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.07489529440748953,
554
+ "grad_norm": 0.27122068405151367,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 0.6182,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.07588075880758807,
561
+ "grad_norm": 0.28131553530693054,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 0.6974,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.07686622320768663,
568
+ "grad_norm": 0.26899459958076477,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 0.6486,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.07785168760778517,
575
+ "grad_norm": 0.31664565205574036,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 0.7727,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.07883715200788372,
582
+ "grad_norm": 0.28200066089630127,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 0.643,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.07982261640798226,
589
+ "grad_norm": 0.3218248188495636,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 0.7016,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.08080808080808081,
596
+ "grad_norm": 0.32966381311416626,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 0.7472,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.08179354520817936,
603
+ "grad_norm": 0.31329721212387085,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 0.7025,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0827790096082779,
610
+ "grad_norm": 0.29452916979789734,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 0.6234,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.08376447400837644,
617
+ "grad_norm": 0.34324830770492554,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 0.6944,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.084749938408475,
624
+ "grad_norm": 0.33645856380462646,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 0.6598,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.08573540280857354,
631
+ "grad_norm": 0.33191972970962524,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 0.6206,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.08672086720867209,
638
+ "grad_norm": 0.4066058099269867,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 0.7335,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.08770633160877063,
645
+ "grad_norm": 0.37192967534065247,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 0.6201,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.08869179600886919,
652
+ "grad_norm": 0.40204325318336487,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 0.691,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.08967726040896773,
659
+ "grad_norm": 0.3774620592594147,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 0.6234,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.09066272480906627,
666
+ "grad_norm": 0.38905617594718933,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 0.5785,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.09164818920916482,
673
+ "grad_norm": 0.40719079971313477,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 0.7717,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.09263365360926337,
680
+ "grad_norm": 0.42338162660598755,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 0.7243,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.09361911800936192,
687
+ "grad_norm": 0.4960746169090271,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 0.694,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.09460458240946046,
694
+ "grad_norm": 0.45286256074905396,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 0.7173,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.095590046809559,
701
+ "grad_norm": 0.47811850905418396,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 0.7395,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.09657551120965756,
708
+ "grad_norm": 0.5401033759117126,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 0.7726,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0975609756097561,
715
+ "grad_norm": 0.6063845157623291,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 0.8667,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.09854644000985464,
722
+ "grad_norm": 0.7505123615264893,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 0.6364,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.09854644000985464,
729
+ "eval_loss": 0.6039547920227051,
730
+ "eval_runtime": 159.9711,
731
+ "eval_samples_per_second": 10.683,
732
+ "eval_steps_per_second": 5.345,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.7046203439828173e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null