aleegis12 commited on
Commit
e3ee53a
·
verified ·
1 Parent(s): f170651

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 sha256:91420910baab2af07db922a3f73e719f5ccc9f92d07777ad02bb7edb1af60045
3
  size 121155320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c452a16c16f1048f4c03754b2666f72ab912305061365d1ced2f8d54817d66
3
  size 121155320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3db20f992d6d774eb5618999f7aa75b1864fd22b0c9080ec792fe147c5e865ef
3
  size 61896852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd2b73fe895a8a4cc75f91b9e0b034bc82cec9524bedf7709abf103d24c0f3f
3
  size 61896852
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48f4b97d80d51a5cf5d8fb92ac3d361e8cb9d64b99197af851dba094c9485166
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ea997b506765681fdb24a01fcb13d70469330deec34bde18a06eceaca6910f
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": 3.407155990600586,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.3241491085899514,
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": 59.055,
374
  "eval_steps_per_second": 14.764,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3412622888140800.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.1993484497070312,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.6482982171799028,
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": 59.055,
374
  "eval_steps_per_second": 14.764,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.33063209076175043,
379
+ "grad_norm": 1.031606912612915,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 3.4814,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.3371150729335494,
386
+ "grad_norm": 1.012144684791565,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 3.0972,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.34359805510534847,
393
+ "grad_norm": 1.0538456439971924,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 3.4517,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3500810372771475,
400
+ "grad_norm": 1.089782476425171,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 3.3362,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.3565640194489465,
407
+ "grad_norm": 1.0148874521255493,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.4717,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.36304700162074555,
414
+ "grad_norm": 1.0671885013580322,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 3.3098,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.3695299837925446,
421
+ "grad_norm": 1.080293893814087,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 3.2466,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.3760129659643436,
428
+ "grad_norm": 1.1275016069412231,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 3.2311,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.3824959481361426,
435
+ "grad_norm": 1.1703333854675293,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 3.4903,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3889789303079417,
442
+ "grad_norm": 1.1692801713943481,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 3.0968,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.39546191247974066,
449
+ "grad_norm": 1.2943613529205322,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 3.3956,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.4019448946515397,
456
+ "grad_norm": 1.2076880931854248,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 3.4592,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.40842787682333875,
463
+ "grad_norm": 1.3995380401611328,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 3.3807,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.41491085899513774,
470
+ "grad_norm": 1.3586690425872803,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 3.2966,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.4213938411669368,
477
+ "grad_norm": 1.359994649887085,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 3.3712,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.42787682333873583,
484
+ "grad_norm": 1.5300426483154297,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 3.4098,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.4343598055105348,
491
+ "grad_norm": 1.7160489559173584,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 3.3961,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.44084278768233387,
498
+ "grad_norm": 1.6259511709213257,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 3.6358,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.4473257698541329,
505
+ "grad_norm": 1.7580747604370117,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 3.3248,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.4538087520259319,
512
+ "grad_norm": 1.9767115116119385,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 3.2761,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.46029173419773095,
519
+ "grad_norm": 2.133505344390869,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 3.4892,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.46677471636953,
526
+ "grad_norm": 2.5297980308532715,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 3.3459,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.473257698541329,
533
+ "grad_norm": 2.724898099899292,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 3.2947,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.47974068071312803,
540
+ "grad_norm": 3.1555697917938232,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 3.4557,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.4862236628849271,
547
+ "grad_norm": 3.3250153064727783,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.9288,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.49270664505672607,
554
+ "grad_norm": 5.941638469696045,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 3.1569,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.4991896272285251,
561
+ "grad_norm": 1.0539709329605103,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.8805,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5056726094003241,
568
+ "grad_norm": 1.1901050806045532,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.9988,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5121555915721232,
575
+ "grad_norm": 1.0893672704696655,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 3.1139,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.5186385737439222,
582
+ "grad_norm": 1.090607762336731,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.9885,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5251215559157212,
589
+ "grad_norm": 0.9755169749259949,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 3.0238,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5316045380875203,
596
+ "grad_norm": 0.9265464544296265,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 3.0336,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.5380875202593193,
603
+ "grad_norm": 0.9207394123077393,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 3.1685,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5445705024311183,
610
+ "grad_norm": 0.8276278972625732,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.9041,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5510534846029174,
617
+ "grad_norm": 0.7896760106086731,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 3.1384,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.5575364667747164,
624
+ "grad_norm": 0.8650602102279663,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 3.1776,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.5640194489465153,
631
+ "grad_norm": 0.7942522168159485,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.9668,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.5705024311183144,
638
+ "grad_norm": 0.868003249168396,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 3.0804,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.5769854132901134,
645
+ "grad_norm": 0.9763777852058411,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 3.0785,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.5834683954619124,
652
+ "grad_norm": 17.73986053466797,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 3.1134,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.5899513776337115,
659
+ "grad_norm": 0.9874743223190308,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 3.3085,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.5964343598055105,
666
+ "grad_norm": 0.9981576800346375,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.15,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.6029173419773096,
673
+ "grad_norm": 1.0464242696762085,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 3.251,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.6094003241491086,
680
+ "grad_norm": 1.119978904724121,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 3.1136,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6158833063209076,
687
+ "grad_norm": 1.084312081336975,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 3.2541,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.6223662884927067,
694
+ "grad_norm": 1.0629708766937256,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 3.1018,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.6288492706645057,
701
+ "grad_norm": 1.205837607383728,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.2119,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.6353322528363047,
708
+ "grad_norm": 1.4000663757324219,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 3.3012,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.6418152350081038,
715
+ "grad_norm": 1.2465779781341553,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 3.2355,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.6482982171799028,
722
+ "grad_norm": 1.313493251800537,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 3.3348,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.6482982171799028,
729
+ "eval_loss": 3.1993484497070312,
730
+ "eval_runtime": 4.3952,
731
+ "eval_samples_per_second": 59.155,
732
+ "eval_steps_per_second": 14.789,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6775304953528320.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null