aleegis09 commited on
Commit
1f7b59b
·
verified ·
1 Parent(s): 40b4d8d

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:ce99e02d4c5b375d7128443008d41020ac126877533a7d12ca77ab5d47bd2aa5
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3061de0e35941e1a471b70cae4757ef7d566f9a8135f455dd07d61683e0f8f6f
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76b44734a6cfd3d1f3356c40eabfecbadd0bab511fbe539f99b1ec0fa0354235
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461cd7529c29aa47e7f947258259a88e4222d3b4f4e631be2533a108c30d5470
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2357966d4a803e8a4454d83db63da35b2a66fef55b950431cbe8a5d424a4d659
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd8e1030dbf8f31b3c22877ed0bb7fbd1d097cbd76e55bba3b995d18e520ad2
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": 1.7766997814178467,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.25477707006369427,
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": 13.335,
374
  "eval_steps_per_second": 3.344,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.54256789372928e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.596757173538208,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.5095541401273885,
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": 13.335,
374
  "eval_steps_per_second": 3.344,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.25987261146496815,
379
+ "grad_norm": 2.453874111175537,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.654,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.26496815286624203,
386
+ "grad_norm": 1.8163388967514038,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.4758,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2700636942675159,
393
+ "grad_norm": 1.19365394115448,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.3972,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.2751592356687898,
400
+ "grad_norm": 1.4323458671569824,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.5399,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.2802547770700637,
407
+ "grad_norm": 1.2911094427108765,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.3959,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.28535031847133757,
414
+ "grad_norm": 1.2983102798461914,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.4503,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.29044585987261146,
421
+ "grad_norm": 1.282852292060852,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.4422,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.29554140127388534,
428
+ "grad_norm": 1.1919018030166626,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.4764,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.3006369426751592,
435
+ "grad_norm": 1.0220428705215454,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.4482,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3057324840764331,
442
+ "grad_norm": 1.004325032234192,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.3913,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.310828025477707,
449
+ "grad_norm": 1.0730646848678589,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.5228,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.3159235668789809,
456
+ "grad_norm": 1.0348135232925415,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.3824,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.32101910828025476,
463
+ "grad_norm": 1.055734634399414,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.2925,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.32611464968152865,
470
+ "grad_norm": 1.2250598669052124,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.4025,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.33121019108280253,
477
+ "grad_norm": 1.2325644493103027,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.4504,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3363057324840764,
484
+ "grad_norm": 1.2184557914733887,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.4286,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3414012738853503,
491
+ "grad_norm": 1.387960433959961,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.5632,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.3464968152866242,
498
+ "grad_norm": 1.1769790649414062,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.3765,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.35159235668789807,
505
+ "grad_norm": 1.2014427185058594,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.4774,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.35668789808917195,
512
+ "grad_norm": 1.1256524324417114,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.4444,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.36178343949044584,
519
+ "grad_norm": 1.1236120462417603,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.4237,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.3668789808917197,
526
+ "grad_norm": 1.0599284172058105,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.3492,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.3719745222929936,
533
+ "grad_norm": 1.1497225761413574,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.3502,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.37707006369426754,
540
+ "grad_norm": 1.144227385520935,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.4483,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.3821656050955414,
547
+ "grad_norm": 1.3062736988067627,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.4855,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.3872611464968153,
554
+ "grad_norm": 1.2697646617889404,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.5133,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3923566878980892,
561
+ "grad_norm": 1.261718988418579,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.405,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3974522292993631,
568
+ "grad_norm": 1.264968752861023,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.5037,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.40254777070063696,
575
+ "grad_norm": 1.289087176322937,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.465,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.40764331210191085,
582
+ "grad_norm": 1.2691148519515991,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.4851,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.41273885350318473,
589
+ "grad_norm": 1.3029874563217163,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.4492,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.4178343949044586,
596
+ "grad_norm": 1.2333258390426636,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.4576,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.4229299363057325,
603
+ "grad_norm": 1.300815224647522,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.4976,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.4280254777070064,
610
+ "grad_norm": 1.2724026441574097,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.4167,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.43312101910828027,
617
+ "grad_norm": 1.3012876510620117,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.4261,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.43821656050955415,
624
+ "grad_norm": 1.2972036600112915,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.3443,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.44331210191082804,
631
+ "grad_norm": 1.3304251432418823,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.4889,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.4484076433121019,
638
+ "grad_norm": 1.4206112623214722,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.4442,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.4535031847133758,
645
+ "grad_norm": 1.456225872039795,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.493,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.4585987261146497,
652
+ "grad_norm": 1.5380885601043701,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.4774,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.4636942675159236,
659
+ "grad_norm": 1.54289710521698,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.6233,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.46878980891719746,
666
+ "grad_norm": 1.3833653926849365,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.4643,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.47388535031847134,
673
+ "grad_norm": 1.5661531686782837,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.5152,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4789808917197452,
680
+ "grad_norm": 1.4505186080932617,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.4569,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4840764331210191,
687
+ "grad_norm": 1.4179692268371582,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.5164,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.489171974522293,
694
+ "grad_norm": 1.643911361694336,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.4666,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.4942675159235669,
701
+ "grad_norm": 1.7628129720687866,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.5073,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.49936305732484076,
708
+ "grad_norm": 1.8917542695999146,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.4153,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.5044585987261146,
715
+ "grad_norm": 2.2565598487854004,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.6597,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.5095541401273885,
722
+ "grad_norm": 2.1938929557800293,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.6038,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.5095541401273885,
729
+ "eval_loss": 1.596757173538208,
730
+ "eval_runtime": 24.8427,
731
+ "eval_samples_per_second": 13.324,
732
+ "eval_steps_per_second": 3.341,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.508513578745856e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null