prxy5607 commited on
Commit
7f4b117
·
verified ·
1 Parent(s): fb28189

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 sha256:44b914fac464622a3290880d2c97fba851afe1ddb850635cbad3fe2e743f0531
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fd0bca76b500e8e54efebf078dd848c37402eec688cf6ae8326cd9e151c03d
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca02122a4c009b080dcc76102432174a52da0588e7a7890fbe2c6a1a5c37f81e
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0e39c9b6132b35d9f19a0802a9b91cdfed743a07b14e05568d1248757f6e91
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fce82ac2d02d86acd238aca60f39378cf0493e53b13ba5a5114b937c5355baac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab5e2e403cce2f08514f8324f4f184a6f7e023b57ce75530dae430d563101901
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.857905387878418,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.04580852038479157,
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": 12.838,
374
  "eval_steps_per_second": 3.211,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.22654807898194e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8161656856536865,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.09161704076958314,
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": 12.838,
374
  "eval_steps_per_second": 3.211,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0467246907924874,
379
+ "grad_norm": 4.632282257080078,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 3.3263,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.04764086120018323,
386
+ "grad_norm": 3.454362154006958,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 3.4455,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.04855703160787907,
393
+ "grad_norm": 2.2924325466156006,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 3.1865,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.049473202015574896,
400
+ "grad_norm": 2.3359978199005127,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 3.2213,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.050389372423270726,
407
+ "grad_norm": 2.6054296493530273,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.4569,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.05130554283096656,
414
+ "grad_norm": 2.411471366882324,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 3.4058,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.05222171323866239,
421
+ "grad_norm": 2.5202689170837402,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 3.1101,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.05313788364635822,
428
+ "grad_norm": 2.3162035942077637,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 3.2279,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.05405405405405406,
435
+ "grad_norm": 2.292923927307129,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 3.2233,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.054970224461749886,
442
+ "grad_norm": 2.277437925338745,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 3.2655,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.055886394869445716,
449
+ "grad_norm": 2.4472885131835938,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 3.356,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.056802565277141545,
456
+ "grad_norm": 2.4935200214385986,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 3.3415,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.05771873568483738,
463
+ "grad_norm": 2.3300907611846924,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 3.2716,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.05863490609253321,
470
+ "grad_norm": 2.2986490726470947,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 3.2727,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.05955107650022904,
477
+ "grad_norm": 2.3526642322540283,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 3.2887,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.060467246907924876,
484
+ "grad_norm": 2.36346697807312,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 3.1683,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.061383417315620706,
491
+ "grad_norm": 2.218932628631592,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 3.3704,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.062299587723316535,
498
+ "grad_norm": 2.328066110610962,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 3.2611,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.06321575813101236,
505
+ "grad_norm": 2.4511618614196777,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 3.2324,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0641319285387082,
512
+ "grad_norm": 2.322838544845581,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 3.1691,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.06504809894640404,
519
+ "grad_norm": 2.294978380203247,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 3.0479,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.06596426935409987,
526
+ "grad_norm": 2.4404642581939697,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 3.1572,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.0668804397617957,
533
+ "grad_norm": 2.3828468322753906,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 3.0854,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.06779661016949153,
540
+ "grad_norm": 2.5379884243011475,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 3.3354,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.06871278057718735,
547
+ "grad_norm": 2.5061211585998535,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 3.3212,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.06962895098488318,
554
+ "grad_norm": 2.3468308448791504,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 3.2781,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.07054512139257901,
561
+ "grad_norm": 2.3657217025756836,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 3.2078,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.07146129180027486,
568
+ "grad_norm": 2.379638671875,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 3.1101,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.07237746220797069,
575
+ "grad_norm": 2.3256547451019287,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 3.1999,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.07329363261566652,
582
+ "grad_norm": 2.40804123878479,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 3.2508,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.07420980302336234,
589
+ "grad_norm": 2.463440418243408,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 3.1665,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.07512597343105817,
596
+ "grad_norm": 2.5652084350585938,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 3.2652,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.076042143838754,
603
+ "grad_norm": 2.472507953643799,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 3.2888,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.07695831424644985,
610
+ "grad_norm": 2.509007453918457,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 3.2122,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.07787448465414568,
617
+ "grad_norm": 2.4399054050445557,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 3.1636,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0787906550618415,
624
+ "grad_norm": 2.5819153785705566,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 3.356,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.07970682546953733,
631
+ "grad_norm": 2.5383763313293457,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 3.2435,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.08062299587723316,
638
+ "grad_norm": 2.4706544876098633,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 3.346,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.081539166284929,
645
+ "grad_norm": 2.4567182064056396,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 3.2462,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.08245533669262482,
652
+ "grad_norm": 2.5329692363739014,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 3.1573,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.08337150710032067,
659
+ "grad_norm": 2.5082852840423584,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 3.1434,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0842876775080165,
666
+ "grad_norm": 2.5499184131622314,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.1346,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.08520384791571232,
673
+ "grad_norm": 2.5437309741973877,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 3.1203,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.08612001832340815,
680
+ "grad_norm": 2.560912609100342,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.9664,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.08703618873110398,
687
+ "grad_norm": 2.5366506576538086,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.9797,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.08795235913879981,
694
+ "grad_norm": 2.702955722808838,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 3.1788,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.08886852954649564,
701
+ "grad_norm": 2.691070795059204,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.0511,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.08978469995419149,
708
+ "grad_norm": 2.8578526973724365,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 3.0515,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.09070087036188731,
715
+ "grad_norm": 3.083177089691162,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 3.1002,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.09161704076958314,
722
+ "grad_norm": 3.706963300704956,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 3.1031,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.09161704076958314,
729
+ "eval_loss": 0.8161656856536865,
730
+ "eval_runtime": 143.009,
731
+ "eval_samples_per_second": 12.859,
732
+ "eval_steps_per_second": 3.217,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.445309615796388e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null