nttx commited on
Commit
f5dd93a
·
verified ·
1 Parent(s): 977f8ac

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 sha256:8bc795940f7cc2e48cab9cba8325c9c5c8e447a1412d39f07f516acbb334c3bf
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221c5594c41f7cedbd2029c645280f9fe3f7a342bddd86341038c049de699670
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c515511a2454676d79b90fc0e64802624e129003a29f07361fc583d1601272d9
3
  size 101184122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc8e3a8ad8a5082129dc45d0d7cdb20acc68a49d301dea02abd097ca424fca6
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:d6e5ae6f85bb6d173881b53df818576ba9b43ae4c7911f7f3f4e057a627c04fb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d87c05d20a02b6dd7b25284c06519d14aee8fd5f30c84b801d9b61f375e6e65f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
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": 1.6872836351394653,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.4624277456647399,
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": 39.553,
374
  "eval_steps_per_second": 9.997,
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": 1.145172758888448e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6507114171981812,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.9248554913294798,
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": 39.553,
374
  "eval_steps_per_second": 9.997,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.47167630057803467,
379
+ "grad_norm": 1.1581029891967773,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 1.3558,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.48092485549132946,
386
+ "grad_norm": 2.36186146736145,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 1.535,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.49017341040462425,
393
+ "grad_norm": 1.2489032745361328,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 1.3911,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.49942196531791905,
400
+ "grad_norm": 1.1275995969772339,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 1.5852,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.5086705202312138,
407
+ "grad_norm": 1.0193781852722168,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 1.8392,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.5179190751445086,
414
+ "grad_norm": 1.486534833908081,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 1.699,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.5271676300578034,
421
+ "grad_norm": 1.0697484016418457,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 1.7594,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.5364161849710982,
428
+ "grad_norm": 0.9851034879684448,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 1.6634,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.545664739884393,
435
+ "grad_norm": 1.8182729482650757,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 1.7782,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.5549132947976878,
442
+ "grad_norm": 0.8374244570732117,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 1.6614,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.5641618497109827,
449
+ "grad_norm": 1.1986464262008667,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 1.776,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.5734104046242775,
456
+ "grad_norm": 1.0033228397369385,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 1.7769,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.5826589595375723,
463
+ "grad_norm": 0.8330934047698975,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 1.8271,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.5919075144508671,
470
+ "grad_norm": 0.8349994421005249,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 1.7522,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.6011560693641619,
477
+ "grad_norm": 1.0363408327102661,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 1.6882,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.6104046242774567,
484
+ "grad_norm": 0.9204206466674805,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 1.703,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.6196531791907515,
491
+ "grad_norm": 0.9362404346466064,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 1.7492,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.6289017341040463,
498
+ "grad_norm": 1.4139052629470825,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 1.6931,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.638150289017341,
505
+ "grad_norm": 1.0456236600875854,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 1.7416,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.6473988439306358,
512
+ "grad_norm": 0.9161862730979919,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 1.7657,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.6566473988439306,
519
+ "grad_norm": 0.963921308517456,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 1.6845,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.6658959537572254,
526
+ "grad_norm": 1.0129166841506958,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 1.7312,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.6751445086705202,
533
+ "grad_norm": 0.9295704364776611,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 1.7409,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.684393063583815,
540
+ "grad_norm": 2.223339319229126,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 1.7596,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.6936416184971098,
547
+ "grad_norm": 0.9056817889213562,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 1.6705,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.7028901734104046,
554
+ "grad_norm": 1.0185023546218872,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 1.6623,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.7121387283236994,
561
+ "grad_norm": 0.9482372999191284,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 1.6812,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.7213872832369942,
568
+ "grad_norm": 1.3618500232696533,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 1.5927,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.730635838150289,
575
+ "grad_norm": 1.399502158164978,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 1.6183,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.7398843930635838,
582
+ "grad_norm": 1.9153316020965576,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 1.2548,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.7491329479768786,
589
+ "grad_norm": 1.786373257637024,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 1.4922,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.7583815028901734,
596
+ "grad_norm": 0.9139667749404907,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 1.8519,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.7676300578034682,
603
+ "grad_norm": 0.7682838439941406,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 1.7448,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.776878612716763,
610
+ "grad_norm": 1.198505163192749,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 1.7318,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.7861271676300579,
617
+ "grad_norm": 1.6691570281982422,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 1.66,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.7953757225433526,
624
+ "grad_norm": 0.8174700140953064,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 1.7503,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.8046242774566474,
631
+ "grad_norm": 1.4348268508911133,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 1.7559,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.8138728323699422,
638
+ "grad_norm": 1.2280317544937134,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 1.7093,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.823121387283237,
645
+ "grad_norm": 1.0251600742340088,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 1.7171,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.8323699421965318,
652
+ "grad_norm": 1.1787769794464111,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 1.7733,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.8416184971098266,
659
+ "grad_norm": 1.0834810733795166,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 1.6628,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.8508670520231214,
666
+ "grad_norm": 1.1346598863601685,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 1.6353,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.8601156069364162,
673
+ "grad_norm": 1.5795148611068726,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 1.63,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.869364161849711,
680
+ "grad_norm": 0.8253781199455261,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 1.6511,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.8786127167630058,
687
+ "grad_norm": 0.9431250691413879,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 1.6856,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.8878612716763006,
694
+ "grad_norm": 1.1542280912399292,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 1.6746,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.8971098265895954,
701
+ "grad_norm": 1.2524795532226562,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 1.6735,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.9063583815028902,
708
+ "grad_norm": 0.8255431056022644,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 1.7712,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.915606936416185,
715
+ "grad_norm": 1.7084015607833862,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 1.6268,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.9248554913294798,
722
+ "grad_norm": 0.9784784317016602,
723
+ "learning_rate": 0.0,
724
+ "loss": 1.6986,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.9248554913294798,
729
+ "eval_loss": 1.6507114171981812,
730
+ "eval_runtime": 4.5144,
731
+ "eval_samples_per_second": 40.315,
732
+ "eval_steps_per_second": 10.19,
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": 2.277478408126464e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null