nttx commited on
Commit
40cc20c
·
verified ·
1 Parent(s): 56557d7

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 sha256:4e83cdcdc40c06f34270d642f2a210b6274320ecbd1aae5d5a2a5549bc4b3aeb
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e1ecd5ae1796a40c42cc53e2b8baa6ae9e576fdaf8002f53d5fc55ab6bbe2f
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9ea358d6504e20e78a30db833657efd6205b00cc5fde3ab7cde971fd9dcdd85
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74f45887eb2bf8a4c01583be5dd4fbec0a4170f7a4e1472ab36942385358ca4
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:aa76c6d21ca243bcfa53ebcdcbf2b0d31aa826505d3d1e738aa835815512076b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f46da81ba631b64de591d5d73e697ebef2af8b3cb47a5eff2c98fdadd25e3f5
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": 0.037399664521217346,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.016857720836142953,
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": 12.306,
374
  "eval_steps_per_second": 6.154,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.19077308849193e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.02691887505352497,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.033715441672285906,
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": 12.306,
374
  "eval_steps_per_second": 6.154,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.017194875252865813,
379
+ "grad_norm": 6.155975341796875,
380
+ "learning_rate": 9.628188298907782e-05,
381
+ "loss": 0.169,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.01753202966958867,
386
+ "grad_norm": 2.993195056915283,
387
+ "learning_rate": 9.592434928729616e-05,
388
+ "loss": 0.1762,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.01786918408631153,
393
+ "grad_norm": 2.0027689933776855,
394
+ "learning_rate": 9.555113246230442e-05,
395
+ "loss": 0.0609,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01820633850303439,
400
+ "grad_norm": 2.9277846813201904,
401
+ "learning_rate": 9.516235996730645e-05,
402
+ "loss": 0.088,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.018543492919757248,
407
+ "grad_norm": 5.291700839996338,
408
+ "learning_rate": 9.475816456775313e-05,
409
+ "loss": 0.0758,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.018880647336480108,
414
+ "grad_norm": 4.0121893882751465,
415
+ "learning_rate": 9.43386842960031e-05,
416
+ "loss": 0.1181,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.01921780175320297,
421
+ "grad_norm": 3.088758945465088,
422
+ "learning_rate": 9.39040624041849e-05,
423
+ "loss": 0.0663,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.019554956169925825,
428
+ "grad_norm": 5.164242744445801,
429
+ "learning_rate": 9.345444731527642e-05,
430
+ "loss": 0.126,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.019892110586648686,
435
+ "grad_norm": 5.446705341339111,
436
+ "learning_rate": 9.298999257241863e-05,
437
+ "loss": 0.039,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.020229265003371546,
442
+ "grad_norm": 1.3323512077331543,
443
+ "learning_rate": 9.251085678648072e-05,
444
+ "loss": 0.0232,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.020566419420094403,
449
+ "grad_norm": 4.320119857788086,
450
+ "learning_rate": 9.201720358189464e-05,
451
+ "loss": 0.0793,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.020903573836817263,
456
+ "grad_norm": 2.836113929748535,
457
+ "learning_rate": 9.150920154077754e-05,
458
+ "loss": 0.045,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.02124072825354012,
463
+ "grad_norm": 3.192572593688965,
464
+ "learning_rate": 9.098702414536107e-05,
465
+ "loss": 0.0605,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.02157788267026298,
470
+ "grad_norm": 5.8117995262146,
471
+ "learning_rate": 9.045084971874738e-05,
472
+ "loss": 0.0745,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.02191503708698584,
477
+ "grad_norm": 2.2573840618133545,
478
+ "learning_rate": 8.9900861364012e-05,
479
+ "loss": 0.0143,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.022252191503708697,
484
+ "grad_norm": 5.993143558502197,
485
+ "learning_rate": 8.933724690167417e-05,
486
+ "loss": 0.1675,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.022589345920431558,
491
+ "grad_norm": 12.099316596984863,
492
+ "learning_rate": 8.876019880555649e-05,
493
+ "loss": 0.2099,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.022926500337154418,
498
+ "grad_norm": 8.319787979125977,
499
+ "learning_rate": 8.816991413705516e-05,
500
+ "loss": 0.2096,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.023263654753877275,
505
+ "grad_norm": 3.1334519386291504,
506
+ "learning_rate": 8.756659447784368e-05,
507
+ "loss": 0.0677,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.023600809170600135,
512
+ "grad_norm": 3.2885525226593018,
513
+ "learning_rate": 8.695044586103296e-05,
514
+ "loss": 0.0135,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.023937963587322995,
519
+ "grad_norm": 3.7970714569091797,
520
+ "learning_rate": 8.632167870081121e-05,
521
+ "loss": 0.0317,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.024275118004045852,
526
+ "grad_norm": 6.135300636291504,
527
+ "learning_rate": 8.568050772058762e-05,
528
+ "loss": 0.1099,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.024612272420768713,
533
+ "grad_norm": 8.074009895324707,
534
+ "learning_rate": 8.502715187966455e-05,
535
+ "loss": 0.1517,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.024949426837491573,
540
+ "grad_norm": 4.536118507385254,
541
+ "learning_rate": 8.436183429846313e-05,
542
+ "loss": 0.0957,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.02528658125421443,
547
+ "grad_norm": 1.107986330986023,
548
+ "learning_rate": 8.368478218232787e-05,
549
+ "loss": 0.0167,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02562373567093729,
554
+ "grad_norm": 5.888400077819824,
555
+ "learning_rate": 8.299622674393614e-05,
556
+ "loss": 0.1375,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.025960890087660147,
561
+ "grad_norm": 1.8470762968063354,
562
+ "learning_rate": 8.229640312433937e-05,
563
+ "loss": 0.0266,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.026298044504383007,
568
+ "grad_norm": 3.479485034942627,
569
+ "learning_rate": 8.158555031266254e-05,
570
+ "loss": 0.0995,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.026635198921105867,
575
+ "grad_norm": 8.64280891418457,
576
+ "learning_rate": 8.086391106448965e-05,
577
+ "loss": 0.1513,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.026972353337828724,
582
+ "grad_norm": 9.630158424377441,
583
+ "learning_rate": 8.013173181896283e-05,
584
+ "loss": 0.2062,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.027309507754551585,
589
+ "grad_norm": 4.263245582580566,
590
+ "learning_rate": 7.938926261462366e-05,
591
+ "loss": 0.0471,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.027646662171274445,
596
+ "grad_norm": 1.5566385984420776,
597
+ "learning_rate": 7.863675700402526e-05,
598
+ "loss": 0.0206,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.027983816587997302,
603
+ "grad_norm": 5.3694539070129395,
604
+ "learning_rate": 7.787447196714427e-05,
605
+ "loss": 0.0735,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.028320971004720162,
610
+ "grad_norm": 8.812443733215332,
611
+ "learning_rate": 7.710266782362247e-05,
612
+ "loss": 0.1369,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.028658125421443022,
617
+ "grad_norm": 2.8177266120910645,
618
+ "learning_rate": 7.63216081438678e-05,
619
+ "loss": 0.0169,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.02899527983816588,
624
+ "grad_norm": 6.240541458129883,
625
+ "learning_rate": 7.553155965904535e-05,
626
+ "loss": 0.1315,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02933243425488874,
631
+ "grad_norm": 4.399284839630127,
632
+ "learning_rate": 7.473279216998895e-05,
633
+ "loss": 0.0642,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.029669588671611596,
638
+ "grad_norm": 4.220780372619629,
639
+ "learning_rate": 7.392557845506432e-05,
640
+ "loss": 0.0912,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.030006743088334457,
645
+ "grad_norm": 4.83798885345459,
646
+ "learning_rate": 7.311019417701566e-05,
647
+ "loss": 0.0563,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.030343897505057317,
652
+ "grad_norm": 10.673697471618652,
653
+ "learning_rate": 7.228691778882693e-05,
654
+ "loss": 0.1215,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.030681051921780174,
659
+ "grad_norm": 4.015604019165039,
660
+ "learning_rate": 7.145603043863045e-05,
661
+ "loss": 0.0804,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.031018206338503034,
666
+ "grad_norm": 3.316225290298462,
667
+ "learning_rate": 7.061781587369519e-05,
668
+ "loss": 0.0384,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.031355360755225894,
673
+ "grad_norm": 0.9016729593276978,
674
+ "learning_rate": 6.977256034352712e-05,
675
+ "loss": 0.0101,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03169251517194875,
680
+ "grad_norm": 0.6843580007553101,
681
+ "learning_rate": 6.892055250211552e-05,
682
+ "loss": 0.0065,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03202966958867161,
687
+ "grad_norm": 2.6481974124908447,
688
+ "learning_rate": 6.806208330935766e-05,
689
+ "loss": 0.0522,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03236682400539447,
694
+ "grad_norm": 0.6568281054496765,
695
+ "learning_rate": 6.719744593169641e-05,
696
+ "loss": 0.0057,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03270397842211733,
701
+ "grad_norm": 3.2465243339538574,
702
+ "learning_rate": 6.632693564200416e-05,
703
+ "loss": 0.012,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.033041132838840186,
708
+ "grad_norm": 5.33789587020874,
709
+ "learning_rate": 6.545084971874738e-05,
710
+ "loss": 0.0263,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03337828725556305,
715
+ "grad_norm": 4.04817008972168,
716
+ "learning_rate": 6.456948734446624e-05,
717
+ "loss": 0.1354,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.033715441672285906,
722
+ "grad_norm": 7.151183128356934,
723
+ "learning_rate": 6.368314950360415e-05,
724
+ "loss": 0.0761,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.033715441672285906,
729
+ "eval_loss": 0.02691887505352497,
730
+ "eval_runtime": 406.7579,
731
+ "eval_samples_per_second": 12.28,
732
+ "eval_steps_per_second": 6.141,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.438154617698386e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null