dimasik2987 commited on
Commit
954a0ee
·
verified ·
1 Parent(s): daa7235

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:c30fd16359844b9a21e242f6e01f8be11d43fa4f4d84c387e92e09d2d5fae7ad
3
  size 138995824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6acad46c4896fcef874c1cd4dfd2827fd58b7691ea8b4a615b487306ce5ab63
3
  size 138995824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0267fc74eeb8a557f9090df64339a3408b61e5151f70d058ab1acac8180a3db2
3
  size 71077780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0308a4c7d34a7f696d4a5e77dcbdd4e2c268c4bb67c99be8360d50e0b8c260
3
  size 71077780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b8b3265ecfe9d3534f257b6ac31888e363c2392045823cae87c1dfcb4df6b55
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:502a6b74e374753f7dbf6431843ecdc0c2ba297df42b63ce53490964fe5583fa
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6626a958c42744f62f15b40b71145564a751f3973a73662e664e23d40b38c82
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16c2a0a7f4d1c317518a0a40a7c58dbcf9237e9297de7a3c67a0a8ebfbe5ded
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.2726948261260986,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.06901311249137336,
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": 43.202,
374
  "eval_steps_per_second": 10.907,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 858609942528000.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.09364652633667,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.13802622498274672,
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": 43.202,
374
  "eval_steps_per_second": 10.907,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07039337474120083,
379
+ "grad_norm": 2.035337209701538,
380
+ "learning_rate": 7.873473684210526e-05,
381
+ "loss": 2.4293,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07177363699102829,
386
+ "grad_norm": 1.4800270795822144,
387
+ "learning_rate": 7.820631578947369e-05,
388
+ "loss": 1.8436,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.07315389924085576,
393
+ "grad_norm": 1.2643930912017822,
394
+ "learning_rate": 7.76778947368421e-05,
395
+ "loss": 2.451,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.07453416149068323,
400
+ "grad_norm": 1.1129631996154785,
401
+ "learning_rate": 7.714947368421052e-05,
402
+ "loss": 2.1686,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.0759144237405107,
407
+ "grad_norm": 1.9466997385025024,
408
+ "learning_rate": 7.662105263157896e-05,
409
+ "loss": 3.0566,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.07729468599033816,
414
+ "grad_norm": 1.585560917854309,
415
+ "learning_rate": 7.609263157894737e-05,
416
+ "loss": 2.9491,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.07867494824016563,
421
+ "grad_norm": 1.148253321647644,
422
+ "learning_rate": 7.556421052631579e-05,
423
+ "loss": 2.5166,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0800552104899931,
428
+ "grad_norm": 1.3044848442077637,
429
+ "learning_rate": 7.503578947368421e-05,
430
+ "loss": 2.061,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08143547273982056,
435
+ "grad_norm": 1.3018648624420166,
436
+ "learning_rate": 7.450736842105263e-05,
437
+ "loss": 2.2174,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.08281573498964803,
442
+ "grad_norm": 1.179358720779419,
443
+ "learning_rate": 7.397894736842105e-05,
444
+ "loss": 1.8668,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0841959972394755,
449
+ "grad_norm": 1.4359699487686157,
450
+ "learning_rate": 7.345052631578948e-05,
451
+ "loss": 1.8076,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.08557625948930296,
456
+ "grad_norm": 1.429067611694336,
457
+ "learning_rate": 7.29221052631579e-05,
458
+ "loss": 2.0383,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08695652173913043,
463
+ "grad_norm": 1.4482382535934448,
464
+ "learning_rate": 7.239368421052631e-05,
465
+ "loss": 2.5015,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0883367839889579,
470
+ "grad_norm": 1.7771934270858765,
471
+ "learning_rate": 7.186526315789474e-05,
472
+ "loss": 2.2055,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.08971704623878538,
477
+ "grad_norm": 1.0457968711853027,
478
+ "learning_rate": 7.133684210526316e-05,
479
+ "loss": 1.5984,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09109730848861283,
484
+ "grad_norm": 1.2737748622894287,
485
+ "learning_rate": 7.080842105263158e-05,
486
+ "loss": 1.7775,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0924775707384403,
491
+ "grad_norm": 1.1890259981155396,
492
+ "learning_rate": 7.028e-05,
493
+ "loss": 2.0228,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.09385783298826778,
498
+ "grad_norm": 1.2597479820251465,
499
+ "learning_rate": 6.975157894736843e-05,
500
+ "loss": 2.0629,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.09523809523809523,
505
+ "grad_norm": 1.0471433401107788,
506
+ "learning_rate": 6.922315789473685e-05,
507
+ "loss": 1.7882,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0966183574879227,
512
+ "grad_norm": 1.0744673013687134,
513
+ "learning_rate": 6.869473684210527e-05,
514
+ "loss": 1.7844,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.09799861973775018,
519
+ "grad_norm": 1.393317699432373,
520
+ "learning_rate": 6.816631578947368e-05,
521
+ "loss": 2.1979,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.09937888198757763,
526
+ "grad_norm": 1.4898236989974976,
527
+ "learning_rate": 6.76378947368421e-05,
528
+ "loss": 2.5061,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.1007591442374051,
533
+ "grad_norm": 1.1046738624572754,
534
+ "learning_rate": 6.710947368421052e-05,
535
+ "loss": 1.8938,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.10213940648723258,
540
+ "grad_norm": 1.3718451261520386,
541
+ "learning_rate": 6.658105263157894e-05,
542
+ "loss": 2.5167,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.10351966873706005,
547
+ "grad_norm": 1.2800939083099365,
548
+ "learning_rate": 6.605263157894737e-05,
549
+ "loss": 1.8427,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.1048999309868875,
554
+ "grad_norm": 1.2824013233184814,
555
+ "learning_rate": 6.55242105263158e-05,
556
+ "loss": 1.6855,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.10628019323671498,
561
+ "grad_norm": 1.1829575300216675,
562
+ "learning_rate": 6.499578947368422e-05,
563
+ "loss": 2.1127,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.10766045548654245,
568
+ "grad_norm": 1.4018757343292236,
569
+ "learning_rate": 6.446736842105264e-05,
570
+ "loss": 2.6736,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.1090407177363699,
575
+ "grad_norm": 1.1487196683883667,
576
+ "learning_rate": 6.393894736842105e-05,
577
+ "loss": 2.1348,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.11042097998619738,
582
+ "grad_norm": 1.2489293813705444,
583
+ "learning_rate": 6.341052631578947e-05,
584
+ "loss": 2.4025,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.11180124223602485,
589
+ "grad_norm": 1.379892349243164,
590
+ "learning_rate": 6.288210526315789e-05,
591
+ "loss": 2.1926,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1131815044858523,
596
+ "grad_norm": 1.3127739429473877,
597
+ "learning_rate": 6.235368421052632e-05,
598
+ "loss": 1.6522,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.11456176673567978,
603
+ "grad_norm": 1.0042823553085327,
604
+ "learning_rate": 6.182526315789474e-05,
605
+ "loss": 1.452,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.11594202898550725,
610
+ "grad_norm": 1.0960407257080078,
611
+ "learning_rate": 6.129684210526316e-05,
612
+ "loss": 1.8077,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.11732229123533472,
617
+ "grad_norm": 1.3931646347045898,
618
+ "learning_rate": 6.076842105263158e-05,
619
+ "loss": 1.9234,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.11870255348516218,
624
+ "grad_norm": 1.2463769912719727,
625
+ "learning_rate": 6.024e-05,
626
+ "loss": 2.3322,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.12008281573498965,
631
+ "grad_norm": 1.5501362085342407,
632
+ "learning_rate": 5.971157894736842e-05,
633
+ "loss": 2.214,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.12146307798481712,
638
+ "grad_norm": 1.4971249103546143,
639
+ "learning_rate": 5.9183157894736835e-05,
640
+ "loss": 2.1229,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.12284334023464458,
645
+ "grad_norm": 1.2540746927261353,
646
+ "learning_rate": 5.8654736842105267e-05,
647
+ "loss": 2.319,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.12422360248447205,
652
+ "grad_norm": 1.3296970129013062,
653
+ "learning_rate": 5.8126315789473684e-05,
654
+ "loss": 2.2295,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.12560386473429952,
659
+ "grad_norm": 1.635713815689087,
660
+ "learning_rate": 5.759789473684211e-05,
661
+ "loss": 2.0453,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.12698412698412698,
666
+ "grad_norm": 2.5068306922912598,
667
+ "learning_rate": 5.706947368421053e-05,
668
+ "loss": 3.5522,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.12836438923395446,
673
+ "grad_norm": 1.3130208253860474,
674
+ "learning_rate": 5.6541052631578945e-05,
675
+ "loss": 1.7299,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.12974465148378192,
680
+ "grad_norm": 1.49214768409729,
681
+ "learning_rate": 5.601263157894736e-05,
682
+ "loss": 1.9252,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.13112491373360938,
687
+ "grad_norm": 1.5757135152816772,
688
+ "learning_rate": 5.5484210526315794e-05,
689
+ "loss": 2.0456,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.13250517598343686,
694
+ "grad_norm": 1.3604228496551514,
695
+ "learning_rate": 5.495578947368421e-05,
696
+ "loss": 1.2423,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.13388543823326432,
701
+ "grad_norm": 1.8302099704742432,
702
+ "learning_rate": 5.442736842105264e-05,
703
+ "loss": 2.4817,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.13526570048309178,
708
+ "grad_norm": 1.6365114450454712,
709
+ "learning_rate": 5.3898947368421055e-05,
710
+ "loss": 2.0664,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.13664596273291926,
715
+ "grad_norm": 1.6933999061584473,
716
+ "learning_rate": 5.337052631578947e-05,
717
+ "loss": 1.6216,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.13802622498274672,
722
+ "grad_norm": 3.5092623233795166,
723
+ "learning_rate": 5.284210526315789e-05,
724
+ "loss": 2.9275,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.13802622498274672,
729
+ "eval_loss": 2.09364652633667,
730
+ "eval_runtime": 7.1227,
731
+ "eval_samples_per_second": 42.821,
732
+ "eval_steps_per_second": 10.81,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1717219885056000.0,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null