nttx commited on
Commit
a8be372
·
verified ·
1 Parent(s): fe46ae9

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 sha256:20bf5e0c9c8fc7f9ad818a86cc70e5a122e632c59736b7a51541f09f07332a51
3
  size 130583912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9c5dca8b1514474fa586bbbd991c4405402b315d452d21fd4c8a61d499d22d
3
  size 130583912
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5f25559387ad6700e675b72fd2bf822558430b3ec91ca82de74b2b1da965655
3
  size 261311226
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf0b7787b0c9ce0023df9b8e3339a665ca93e08c95a242ee06f98c588cdeef5
3
  size 261311226
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a633a5d6afcafcfc45fceb3dfc6e312c4376a26c0c471572b611b97489ba081c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c166a7eb832fb83eba3fc08a73ef8ec8d2a1044b61db26131432970448bc19
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": 4.124388217926025,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.007503141940687663,
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": 9.569,
374
  "eval_steps_per_second": 2.392,
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": 9.68801166211154e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.9525041580200195,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.015006283881375326,
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": 9.569,
374
  "eval_steps_per_second": 2.392,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.007653204779501416,
379
+ "grad_norm": 9.979507446289062,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 30.6154,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.007803267618315169,
386
+ "grad_norm": 10.939770698547363,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 31.6489,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.007953330457128923,
393
+ "grad_norm": 11.191797256469727,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 30.9841,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.008103393295942675,
400
+ "grad_norm": 11.720529556274414,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 32.4647,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.00825345613475643,
407
+ "grad_norm": 13.322903633117676,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 33.2152,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.008403518973570183,
414
+ "grad_norm": 12.972123146057129,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 32.6633,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.008553581812383936,
421
+ "grad_norm": 12.695440292358398,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 33.9742,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00870364465119769,
428
+ "grad_norm": 13.083794593811035,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 34.3758,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.008853707490011442,
435
+ "grad_norm": 14.709982872009277,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 33.0617,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009003770328825196,
442
+ "grad_norm": 15.33502197265625,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 32.3498,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.009153833167638948,
449
+ "grad_norm": 16.43514060974121,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 35.4804,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.009303896006452702,
456
+ "grad_norm": 16.312402725219727,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 36.8484,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.009453958845266456,
463
+ "grad_norm": 18.906774520874023,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 37.3672,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.009604021684080208,
470
+ "grad_norm": 17.955244064331055,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 38.5029,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.009754084522893962,
477
+ "grad_norm": 20.66045379638672,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 35.5722,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.009904147361707714,
484
+ "grad_norm": 20.17714500427246,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 37.8927,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.010054210200521468,
491
+ "grad_norm": 22.08597755432129,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 38.4573,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.010204273039335222,
498
+ "grad_norm": 24.34529685974121,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 40.1156,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.010354335878148975,
505
+ "grad_norm": 22.071252822875977,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 40.0515,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.010504398716962729,
512
+ "grad_norm": 23.233043670654297,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 38.8181,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.010654461555776481,
519
+ "grad_norm": 24.044532775878906,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 38.3733,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.010804524394590235,
526
+ "grad_norm": 28.727855682373047,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 38.9866,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.010954587233403987,
533
+ "grad_norm": 31.710817337036133,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 43.0757,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.011104650072217741,
540
+ "grad_norm": 29.618091583251953,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 40.1635,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.011254712911031495,
547
+ "grad_norm": 15.594468116760254,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 31.7493,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.011404775749845247,
554
+ "grad_norm": 16.501638412475586,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 30.6078,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.011554838588659001,
561
+ "grad_norm": 16.97194480895996,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 30.2159,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.011704901427472754,
568
+ "grad_norm": 17.44843864440918,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 29.8036,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.011854964266286508,
575
+ "grad_norm": 15.254544258117676,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 28.1706,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.012005027105100262,
582
+ "grad_norm": 18.066022872924805,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 29.3522,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.012155089943914014,
589
+ "grad_norm": 17.23478126525879,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 30.1829,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.012305152782727768,
596
+ "grad_norm": 16.398849487304688,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 28.8294,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.01245521562154152,
603
+ "grad_norm": 16.836814880371094,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 29.5157,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.012605278460355274,
610
+ "grad_norm": 14.805627822875977,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 30.2987,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.012755341299169026,
617
+ "grad_norm": 16.60382080078125,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 30.1055,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.01290540413798278,
624
+ "grad_norm": 14.74989128112793,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 28.499,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.013055466976796534,
631
+ "grad_norm": 18.09991455078125,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 31.4409,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.013205529815610286,
638
+ "grad_norm": 15.617703437805176,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 29.3455,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.01335559265442404,
645
+ "grad_norm": 17.055313110351562,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 26.5924,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.013505655493237793,
652
+ "grad_norm": 15.88111686706543,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 26.878,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.013655718332051547,
659
+ "grad_norm": 16.348384857177734,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 28.8989,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0138057811708653,
666
+ "grad_norm": 15.886968612670898,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 26.7125,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.013955844009679053,
673
+ "grad_norm": 16.663654327392578,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 27.2911,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.014105906848492807,
680
+ "grad_norm": 17.79175567626953,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 27.798,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01425596968730656,
687
+ "grad_norm": 15.905275344848633,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 26.0851,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.014406032526120313,
694
+ "grad_norm": 16.322898864746094,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 27.9597,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.014556095364934065,
701
+ "grad_norm": 16.844186782836914,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 25.2095,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.01470615820374782,
708
+ "grad_norm": 16.607568740844727,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 24.5913,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.014856221042561573,
715
+ "grad_norm": 15.835559844970703,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 24.0955,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.015006283881375326,
722
+ "grad_norm": 18.256946563720703,
723
+ "learning_rate": 0.0,
724
+ "loss": 25.9992,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.015006283881375326,
729
+ "eval_loss": 3.9525041580200195,
730
+ "eval_runtime": 1173.1028,
731
+ "eval_samples_per_second": 9.568,
732
+ "eval_steps_per_second": 2.392,
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": 1.9392388208787456e+17,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null