bbytxt commited on
Commit
2b0d22d
·
verified ·
1 Parent(s): 4c2920d

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 sha256:6bda09c1373daf309577656663a228de3d1e6559c823ebb11b0811cc45d7719c
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91db19a4d1886e3d0a8dba988e8c4aefb6380137a1722f5877e0f039f09de765
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bed4c004940ed8bf1d9d393b01cb3ca7662104ed0d8defac9830580c87ab93e
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:485c9b189313663c9724f45337f87319abb2c41ca36b1108f95ae33d5605f881
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f7e10c59f828df54614fd5e9e87ba58e7a3d64e4c42cfaad75010f2395f3147
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6d462da0494e11688d71f8b57287cef6ce233aaa1d77af7d51d4af692ff1fa
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": 0.48895522952079773,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.11560693641618497,
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": 13.139,
374
  "eval_steps_per_second": 3.298,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.580280733197926e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4530438780784607,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.23121387283236994,
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": 13.139,
374
  "eval_steps_per_second": 3.298,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.11791907514450867,
379
+ "grad_norm": 0.48289260268211365,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.5234,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.12023121387283237,
386
+ "grad_norm": 0.5483802556991577,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.5555,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.12254335260115606,
393
+ "grad_norm": 0.4908915162086487,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.5437,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.12485549132947976,
400
+ "grad_norm": 0.44201579689979553,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.532,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.12716763005780346,
407
+ "grad_norm": 0.35535645484924316,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.4679,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.12947976878612716,
414
+ "grad_norm": 0.36609333753585815,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.5125,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.13179190751445086,
421
+ "grad_norm": 0.4033358693122864,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.4996,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.13410404624277455,
428
+ "grad_norm": 0.4537183940410614,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.5015,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.13641618497109825,
435
+ "grad_norm": 0.42289552092552185,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.4932,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.13872832369942195,
442
+ "grad_norm": 0.37897226214408875,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.4721,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.14104046242774568,
449
+ "grad_norm": 0.38306698203086853,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.4902,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.14335260115606938,
456
+ "grad_norm": 0.39026594161987305,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.4543,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.14566473988439307,
463
+ "grad_norm": 0.42585158348083496,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.4673,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.14797687861271677,
470
+ "grad_norm": 0.42971956729888916,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.4389,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.15028901734104047,
477
+ "grad_norm": 0.4161655306816101,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.4708,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.15260115606936417,
484
+ "grad_norm": 0.40648549795150757,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.4559,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.15491329479768787,
491
+ "grad_norm": 0.4191438555717468,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.4522,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.15722543352601157,
498
+ "grad_norm": 0.47340279817581177,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.444,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.15953757225433526,
505
+ "grad_norm": 0.4360640048980713,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.4421,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.16184971098265896,
512
+ "grad_norm": 0.4308934807777405,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.4379,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.16416184971098266,
519
+ "grad_norm": 0.40363365411758423,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.3989,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.16647398843930636,
526
+ "grad_norm": 0.44806885719299316,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.4373,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.16878612716763006,
533
+ "grad_norm": 0.41386452317237854,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.4112,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.17109826589595376,
540
+ "grad_norm": 0.4437868893146515,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.4328,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.17341040462427745,
547
+ "grad_norm": 0.4278442859649658,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.4141,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.17572254335260115,
554
+ "grad_norm": 0.4373546540737152,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.428,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.17803468208092485,
561
+ "grad_norm": 0.42723631858825684,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.398,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.18034682080924855,
568
+ "grad_norm": 0.4368928074836731,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.4067,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.18265895953757225,
575
+ "grad_norm": 0.4366152286529541,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.4172,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.18497109826589594,
582
+ "grad_norm": 0.4488803446292877,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.407,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.18728323699421964,
589
+ "grad_norm": 0.4308355450630188,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.3983,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.18959537572254334,
596
+ "grad_norm": 0.43071937561035156,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.4044,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.19190751445086704,
603
+ "grad_norm": 0.49217772483825684,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.412,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.19421965317919074,
610
+ "grad_norm": 0.4487551152706146,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.3821,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.19653179190751446,
617
+ "grad_norm": 0.42099928855895996,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.3856,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.19884393063583816,
624
+ "grad_norm": 0.4627571702003479,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.3734,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.20115606936416186,
631
+ "grad_norm": 0.42417681217193604,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.3633,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.20346820809248556,
638
+ "grad_norm": 0.44514182209968567,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.3745,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.20578034682080926,
645
+ "grad_norm": 0.4584387540817261,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.3893,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.20809248554913296,
652
+ "grad_norm": 0.4498540759086609,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.3769,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.21040462427745665,
659
+ "grad_norm": 0.4657157361507416,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.3816,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.21271676300578035,
666
+ "grad_norm": 0.47834116220474243,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.3824,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.21502890173410405,
673
+ "grad_norm": 0.5006725788116455,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.4205,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.21734104046242775,
680
+ "grad_norm": 0.4631800949573517,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.3384,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.21965317919075145,
687
+ "grad_norm": 0.4934702515602112,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.3953,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.22196531791907514,
694
+ "grad_norm": 0.5679356455802917,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.4398,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.22427745664739884,
701
+ "grad_norm": 0.5142523050308228,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.3823,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.22658959537572254,
708
+ "grad_norm": 0.5662355422973633,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.4076,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.22890173410404624,
715
+ "grad_norm": 0.5996310710906982,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.4301,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.23121387283236994,
722
+ "grad_norm": 0.6809976100921631,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.3711,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.23121387283236994,
729
+ "eval_loss": 0.4530438780784607,
730
+ "eval_runtime": 55.434,
731
+ "eval_samples_per_second": 13.151,
732
+ "eval_steps_per_second": 3.301,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5122848626927206e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null