nttx commited on
Commit
a7b2074
·
verified ·
1 Parent(s): 9d03c70

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 sha256:0b19fbc017b099db0b76d71420017f2501507246a150e2a042e514cc85b249b8
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8b1ff4da052cca5834737b55c0b97ead5e030fc317ceeb584dbab41b83afd9
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:781a40350e59395e8c5fee8e9a5da4278d194d03d870070e7a18c4e0a28693df
3
  size 50721146
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a346e0c7a53e213e08c12d8336c82e2817511d48ee5b8c4e220ec062979c28dc
3
  size 50721146
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c277299c173e92bf52fe4bd52404e9025887b004f29e92a926437fe39f59253
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0e528de94c502eff9ceac37fa973ad8539f2fe8f54bb0f0e01d0a084e56238
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7093144655227661,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.006961849067112225,
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": 46.581,
374
  "eval_steps_per_second": 5.823,
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": 2660236573802496.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7014566659927368,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.01392369813422445,
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": 46.581,
374
  "eval_steps_per_second": 5.823,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.007101086048454469,
379
+ "grad_norm": 0.34465742111206055,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 1.3857,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.007240323029796714,
386
+ "grad_norm": 0.27175235748291016,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 1.2343,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.007379560011138958,
393
+ "grad_norm": 0.36743292212486267,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 1.5124,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.007518796992481203,
400
+ "grad_norm": 0.3471788167953491,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 1.2989,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.007658033973823447,
407
+ "grad_norm": 0.4580748379230499,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 1.6741,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.007797270955165692,
414
+ "grad_norm": 0.4226394295692444,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 1.0777,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.007936507936507936,
421
+ "grad_norm": 0.49509432911872864,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 1.1065,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00807574491785018,
428
+ "grad_norm": 0.41200292110443115,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 0.9241,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.008214981899192425,
435
+ "grad_norm": 0.35977041721343994,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 1.2245,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.00835421888053467,
442
+ "grad_norm": 0.6946668028831482,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 1.6109,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.008493455861876914,
449
+ "grad_norm": 0.4504575729370117,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 1.5427,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.008632692843219159,
456
+ "grad_norm": 0.6242891550064087,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 1.2742,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.008771929824561403,
463
+ "grad_norm": 0.5244201421737671,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 0.9132,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.008911166805903648,
470
+ "grad_norm": 0.5816797614097595,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 1.2874,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.009050403787245892,
477
+ "grad_norm": 0.9515994787216187,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 1.4521,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.009189640768588136,
484
+ "grad_norm": 0.5306954383850098,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 1.1104,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.009328877749930381,
491
+ "grad_norm": 0.48044753074645996,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 1.3081,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.009468114731272625,
498
+ "grad_norm": 0.9126547574996948,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 1.5589,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.00960735171261487,
505
+ "grad_norm": 1.10706627368927,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 1.3117,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.009746588693957114,
512
+ "grad_norm": 0.45162731409072876,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 1.2278,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.009885825675299359,
519
+ "grad_norm": 0.6646483540534973,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 1.2068,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.010025062656641603,
526
+ "grad_norm": 0.5071254968643188,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 1.1403,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.010164299637983848,
533
+ "grad_norm": 0.5382006764411926,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 1.4048,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.010303536619326092,
540
+ "grad_norm": 0.8997327089309692,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 1.4637,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.010442773600668337,
547
+ "grad_norm": 0.7685480117797852,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 1.1736,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.010582010582010581,
554
+ "grad_norm": 0.7356314063072205,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 1.4349,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.010721247563352826,
561
+ "grad_norm": 0.651771068572998,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 1.1144,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.01086048454469507,
568
+ "grad_norm": 0.8967679738998413,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 1.4387,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.010999721526037315,
575
+ "grad_norm": 0.8492909669876099,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 1.6909,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.01113895850737956,
582
+ "grad_norm": 1.6591277122497559,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 1.6175,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.011278195488721804,
589
+ "grad_norm": 0.649274468421936,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 1.206,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.011417432470064048,
596
+ "grad_norm": 0.9369542598724365,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 1.4692,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.011556669451406293,
603
+ "grad_norm": 0.950615644454956,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 1.2868,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.011695906432748537,
610
+ "grad_norm": 1.2293789386749268,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 1.4995,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.011835143414090782,
617
+ "grad_norm": 1.2868958711624146,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 1.3333,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.011974380395433026,
624
+ "grad_norm": 1.319376826286316,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 1.3914,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.01211361737677527,
631
+ "grad_norm": 0.9335888624191284,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 1.7684,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.012252854358117515,
638
+ "grad_norm": 1.3220711946487427,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 1.5438,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.01239209133945976,
645
+ "grad_norm": 1.150991678237915,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 1.7093,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.012531328320802004,
652
+ "grad_norm": 2.8452095985412598,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 1.7566,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.012670565302144249,
659
+ "grad_norm": 1.1532390117645264,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 1.8575,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.012809802283486493,
666
+ "grad_norm": 1.3144155740737915,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 1.8457,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.012949039264828738,
673
+ "grad_norm": 2.25860857963562,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 2.4188,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.013088276246170982,
680
+ "grad_norm": 2.153165817260742,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 2.2073,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.013227513227513227,
687
+ "grad_norm": 3.1395328044891357,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 2.9514,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.013366750208855471,
694
+ "grad_norm": 6.766762733459473,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 3.0856,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.013505987190197716,
701
+ "grad_norm": 4.75481653213501,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 3.3937,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.01364522417153996,
708
+ "grad_norm": 6.400866508483887,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 3.4464,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.013784461152882205,
715
+ "grad_norm": 8.275238037109375,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 3.2241,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.01392369813422445,
722
+ "grad_norm": 8.179410934448242,
723
+ "learning_rate": 0.0,
724
+ "loss": 4.2949,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.01392369813422445,
729
+ "eval_loss": 1.7014566659927368,
730
+ "eval_runtime": 65.155,
731
+ "eval_samples_per_second": 46.412,
732
+ "eval_steps_per_second": 5.802,
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": 5269314751954944.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null