aleegis12 commited on
Commit
397b624
·
verified ·
1 Parent(s): 142cdd2

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:c7865235b5a4adb8cc34268c2f3d260df7abeb160d5d2b7464c8f1cf791d88be
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2aa34985d836571c132bf5954f8b3b651a7ad93e724cb6c9c7725993a260aa3
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80eb53fd572469d7334531d63539c1975038292797784ec40c5945cfed343f0f
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04a0e4cd935a3fde6f99a0efb9f890cf5c40e8d69180cff517aae9add4240e33
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:b20809acd68563f45e537e0af823ce2ce08fe12a3237bad4df8a635cd5784e96
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68a8abe25cdb3844a4fd6c64e39058db181b2d26ead02aa41274f1d8c1b967b
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": 0.796090304851532,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.008840951286358412,
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": 13.565,
374
  "eval_steps_per_second": 3.392,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.15499809800192e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7386493682861328,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.017681902572716825,
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": 13.565,
374
  "eval_steps_per_second": 3.392,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.009017770312085581,
379
+ "grad_norm": 10.096370697021484,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 3.866,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.009194589337812748,
386
+ "grad_norm": 5.29091215133667,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 3.2826,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.009371408363539916,
393
+ "grad_norm": 8.30187702178955,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 3.2665,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.009548227389267085,
400
+ "grad_norm": 8.213489532470703,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 3.3482,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.009725046414994254,
407
+ "grad_norm": 4.872696876525879,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.0297,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009901865440721422,
414
+ "grad_norm": 4.427055835723877,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 3.1758,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.010078684466448589,
421
+ "grad_norm": 4.391081809997559,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 3.0824,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.010255503492175758,
428
+ "grad_norm": 4.616461753845215,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.9979,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.010432322517902926,
435
+ "grad_norm": 5.5998854637146,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 3.1535,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.010609141543630095,
442
+ "grad_norm": 4.823612213134766,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.9943,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.010785960569357263,
449
+ "grad_norm": 4.2810773849487305,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.8258,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.01096277959508443,
456
+ "grad_norm": 4.464574813842773,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 3.0109,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.011139598620811599,
463
+ "grad_norm": 4.964107036590576,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 3.0339,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.011316417646538767,
470
+ "grad_norm": 4.688778400421143,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.8198,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.011493236672265936,
477
+ "grad_norm": 4.536004066467285,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 3.1435,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.011670055697993105,
484
+ "grad_norm": 4.5505475997924805,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.8332,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.011846874723720272,
491
+ "grad_norm": 3.98578143119812,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.7494,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01202369374944744,
498
+ "grad_norm": 4.547332763671875,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.9165,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.012200512775174609,
505
+ "grad_norm": 3.9778659343719482,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.7262,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.012377331800901777,
512
+ "grad_norm": 4.422539710998535,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.8827,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.012554150826628946,
519
+ "grad_norm": 4.440034866333008,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.9343,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.012730969852356113,
526
+ "grad_norm": 4.438572883605957,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.8539,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.012907788878083281,
533
+ "grad_norm": 4.555628776550293,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 3.0262,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01308460790381045,
540
+ "grad_norm": 4.12335729598999,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.85,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.013261426929537619,
547
+ "grad_norm": 4.22313928604126,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.7441,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.013438245955264787,
554
+ "grad_norm": 4.474804401397705,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.832,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.013615064980991954,
561
+ "grad_norm": 4.030309200286865,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.7783,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.013791884006719123,
568
+ "grad_norm": 4.222381591796875,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.9147,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.013968703032446291,
575
+ "grad_norm": 4.298746109008789,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.8797,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.01414552205817346,
582
+ "grad_norm": 4.495664119720459,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 3.0076,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.014322341083900628,
589
+ "grad_norm": 4.467094421386719,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.7632,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.014499160109627795,
596
+ "grad_norm": 4.033594608306885,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.8745,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.014675979135354964,
603
+ "grad_norm": 3.7200775146484375,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.7365,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.014852798161082132,
610
+ "grad_norm": 4.186917781829834,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.7117,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.015029617186809301,
617
+ "grad_norm": 4.097092151641846,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.9168,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.01520643621253647,
624
+ "grad_norm": 4.045411586761475,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.652,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.015383255238263636,
631
+ "grad_norm": 3.9682466983795166,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.7225,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.015560074263990805,
638
+ "grad_norm": 4.498869895935059,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.6963,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.015736893289717974,
645
+ "grad_norm": 4.063172817230225,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.4276,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.015913712315445142,
652
+ "grad_norm": 4.287618160247803,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.532,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.01609053134117231,
659
+ "grad_norm": 4.349016189575195,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.5787,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.01626735036689948,
666
+ "grad_norm": 4.420528888702393,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.7135,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.016444169392626648,
673
+ "grad_norm": 3.8942527770996094,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.4143,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.016620988418353817,
680
+ "grad_norm": 4.0477399826049805,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.4438,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01679780744408098,
687
+ "grad_norm": 4.152792453765869,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.6107,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.01697462646980815,
694
+ "grad_norm": 4.101984977722168,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.5281,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.01715144549553532,
701
+ "grad_norm": 4.297181129455566,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.5312,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.017328264521262488,
708
+ "grad_norm": 4.133391857147217,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.4468,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.017505083546989656,
715
+ "grad_norm": 4.21942663192749,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.4245,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.017681902572716825,
722
+ "grad_norm": 4.527026176452637,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.4347,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.017681902572716825,
729
+ "eval_loss": 0.7386493682861328,
730
+ "eval_runtime": 702.0834,
731
+ "eval_samples_per_second": 13.567,
732
+ "eval_steps_per_second": 3.393,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null