nttx commited on
Commit
e98fb01
·
verified ·
1 Parent(s): 32c0bbd

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 sha256:5d1fd48c8423e66857ed76fcdb01343e791960fc0eb577f25b72ab533688d845
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f42dbbe0451973042f7bac399b20cf01aa394e1acfd51f4cd7fe5593aa24649
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4941cf6a0ad448939a979b53a95b60ba37e5da03e592b2d74527c82d1f9d7622
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9e0858d4806b4e40991c1771885c8e7271effcd608958f56167f8a36a717657
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d9d10ba61c0bd5326894984a03b6dcfde6e68b205f66e99c2103d60611fdeab
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e321bbcb5d2ac2447d5028cb6353754e2799710ca4c7851677b15cc836a84752
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": 7.059117317199707,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.35778175313059035,
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": 10.714,
374
  "eval_steps_per_second": 2.678,
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": 6.53464644354048e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 6.504799842834473,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.7155635062611807,
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": 10.714,
374
  "eval_steps_per_second": 2.678,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.36493738819320215,
379
+ "grad_norm": 70.5916519165039,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 58.9163,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.37209302325581395,
386
+ "grad_norm": 66.9151840209961,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 50.1909,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.37924865831842575,
393
+ "grad_norm": 51.34752655029297,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 53.5236,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.38640429338103754,
400
+ "grad_norm": 63.0931510925293,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 59.101,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.3935599284436494,
407
+ "grad_norm": 71.14337921142578,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 55.9521,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.4007155635062612,
414
+ "grad_norm": 64.30337524414062,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 50.8157,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.407871198568873,
421
+ "grad_norm": 63.9760627746582,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 52.2343,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.4150268336314848,
428
+ "grad_norm": 69.6192855834961,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 55.5242,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.4221824686940966,
435
+ "grad_norm": 76.87415313720703,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 53.0602,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.4293381037567084,
442
+ "grad_norm": 58.04973220825195,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 56.443,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.4364937388193202,
449
+ "grad_norm": 66.81076049804688,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 54.4524,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.44364937388193204,
456
+ "grad_norm": 64.75467681884766,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 57.5205,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.45080500894454384,
463
+ "grad_norm": 54.86395263671875,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 55.5413,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.45796064400715564,
470
+ "grad_norm": 49.26187515258789,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 51.8988,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.46511627906976744,
477
+ "grad_norm": 70.07756805419922,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 58.8367,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.47227191413237923,
484
+ "grad_norm": 61.31855392456055,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 54.1545,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.47942754919499103,
491
+ "grad_norm": 63.78771209716797,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 56.2443,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4865831842576029,
498
+ "grad_norm": 51.51386260986328,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 53.1392,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.4937388193202147,
505
+ "grad_norm": 64.99959564208984,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 45.8676,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.5008944543828264,
512
+ "grad_norm": 122.9439926147461,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 47.0922,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.5080500894454383,
519
+ "grad_norm": 83.07128143310547,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 42.5292,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.5152057245080501,
526
+ "grad_norm": 84.25505828857422,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 43.7117,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.5223613595706619,
533
+ "grad_norm": 74.06256103515625,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 48.1763,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.5295169946332737,
540
+ "grad_norm": 96.82910919189453,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 48.4631,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.5366726296958855,
547
+ "grad_norm": 73.7818832397461,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 46.4936,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.5438282647584973,
554
+ "grad_norm": 98.01385498046875,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 44.3822,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5509838998211091,
561
+ "grad_norm": 100.22280883789062,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 47.598,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5581395348837209,
568
+ "grad_norm": 79.705322265625,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 52.3615,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5652951699463328,
575
+ "grad_norm": 76.27445220947266,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 46.7347,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.5724508050089445,
582
+ "grad_norm": 91.04290771484375,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 45.2536,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5796064400715564,
589
+ "grad_norm": 102.24838256835938,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 46.5595,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5867620751341681,
596
+ "grad_norm": 75.27155303955078,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 50.9991,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.59391771019678,
603
+ "grad_norm": 81.08625793457031,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 44.8026,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.6010733452593918,
610
+ "grad_norm": 102.80239868164062,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 51.6388,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.6082289803220036,
617
+ "grad_norm": 63.9753532409668,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 48.8587,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.6153846153846154,
624
+ "grad_norm": 68.33111572265625,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 51.9723,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.6225402504472272,
631
+ "grad_norm": 73.3394775390625,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 46.4974,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.629695885509839,
638
+ "grad_norm": 54.423213958740234,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 52.1191,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.6368515205724508,
645
+ "grad_norm": 75.42688751220703,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 51.9796,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.6440071556350626,
652
+ "grad_norm": 77.87445068359375,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 51.9779,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.6511627906976745,
659
+ "grad_norm": 73.0838394165039,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 50.208,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.6583184257602862,
666
+ "grad_norm": 63.85371780395508,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 54.3247,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.6654740608228981,
673
+ "grad_norm": 64.33513641357422,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 53.0616,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.6726296958855098,
680
+ "grad_norm": 65.0680160522461,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 55.7809,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6797853309481217,
687
+ "grad_norm": 77.23161315917969,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 54.7041,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.6869409660107334,
694
+ "grad_norm": 55.58324432373047,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 52.5574,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.6940966010733453,
701
+ "grad_norm": 75.79041290283203,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 55.3405,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.7012522361359571,
708
+ "grad_norm": 78.58323669433594,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 54.7342,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.7084078711985689,
715
+ "grad_norm": 76.88545989990234,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 55.309,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.7155635062611807,
722
+ "grad_norm": 73.43214416503906,
723
+ "learning_rate": 0.0,
724
+ "loss": 61.4194,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.7155635062611807,
729
+ "eval_loss": 6.504799842834473,
730
+ "eval_runtime": 22.0165,
731
+ "eval_samples_per_second": 10.719,
732
+ "eval_steps_per_second": 2.68,
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": 1.306929288708096e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null