ancient41 commited on
Commit
8e4b998
·
verified ·
1 Parent(s): 7b41f56

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:c18fc93688d8d70948added4021c38d24b513b5b42a5033d3f1342e32c35dfea
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ee20b2d465c02dc5d6d045a0f073a7519f3921016e437ed09d984b7d4d50b8
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:972a1a4dc487e7c3736c4fe983dfe49d2b564be46ca8cb8daeb2a55feb4a165b
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4634696a27e54eb6a6d62fc061e18e92859e6ef34d0c010a09532c271fe12e1
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f71b24ebd1c39ec06ad20075d1a50ed29b62fe88330edb1adc263c49aadd400
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9477fa0e4be4cf50bb75d29e2e86e534c2df5a3cfd904bd36cd74856e9a18ba
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": 0.6693209409713745,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.35650623885918004,
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": 13.254,
374
  "eval_steps_per_second": 3.313,
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": 0.3400123119354248,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.7130124777183601,
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": 13.254,
374
  "eval_steps_per_second": 3.313,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.36363636363636365,
379
+ "grad_norm": 2.8368263244628906,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.2142,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.37076648841354726,
386
+ "grad_norm": 7.45966911315918,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.2947,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3778966131907308,
393
+ "grad_norm": 3.3990819454193115,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.258,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3850267379679144,
400
+ "grad_norm": 2.759211778640747,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.3852,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.39215686274509803,
407
+ "grad_norm": 4.810303688049316,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.5276,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.39928698752228164,
414
+ "grad_norm": 5.013471603393555,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.3654,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.40641711229946526,
421
+ "grad_norm": 4.822093486785889,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.4552,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.41354723707664887,
428
+ "grad_norm": 4.117964744567871,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.6252,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.4206773618538324,
435
+ "grad_norm": 3.389159679412842,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.3813,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.42780748663101603,
442
+ "grad_norm": 4.948807239532471,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.4031,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.43493761140819964,
449
+ "grad_norm": 2.4192276000976562,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.2109,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.44206773618538325,
456
+ "grad_norm": 2.610354423522949,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.313,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.44919786096256686,
463
+ "grad_norm": 5.960036754608154,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.5946,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.4563279857397504,
470
+ "grad_norm": 3.539583921432495,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.4566,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.46345811051693403,
477
+ "grad_norm": 4.794179916381836,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.4307,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.47058823529411764,
484
+ "grad_norm": 5.651267051696777,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.6152,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.47771836007130125,
491
+ "grad_norm": 8.529621124267578,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.6235,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.48484848484848486,
498
+ "grad_norm": 3.700084924697876,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.3216,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.4919786096256685,
505
+ "grad_norm": 3.2698822021484375,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.443,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.49910873440285203,
512
+ "grad_norm": 5.935876846313477,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.515,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.5062388591800356,
519
+ "grad_norm": 13.412459373474121,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.974,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.5133689839572193,
526
+ "grad_norm": 10.322650909423828,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.6109,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.5204991087344029,
533
+ "grad_norm": 8.35332202911377,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.229,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.5276292335115864,
540
+ "grad_norm": 5.663819313049316,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.7897,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.5347593582887701,
547
+ "grad_norm": 4.571802139282227,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.4717,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.5418894830659536,
554
+ "grad_norm": 2.7498021125793457,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.4664,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5490196078431373,
561
+ "grad_norm": 2.3304195404052734,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.3486,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5561497326203209,
568
+ "grad_norm": 4.024349212646484,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.447,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5632798573975044,
575
+ "grad_norm": 5.358171463012695,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.3599,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.5704099821746881,
582
+ "grad_norm": 1.9654799699783325,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.2669,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5775401069518716,
589
+ "grad_norm": 1.602853536605835,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.2146,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5846702317290553,
596
+ "grad_norm": 3.970834255218506,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.3121,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.5918003565062389,
603
+ "grad_norm": 1.8870638608932495,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.1878,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5989304812834224,
610
+ "grad_norm": 5.286268711090088,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.1967,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.6060606060606061,
617
+ "grad_norm": 5.626857757568359,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.1777,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.6131907308377896,
624
+ "grad_norm": 3.088507890701294,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.1277,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.6203208556149733,
631
+ "grad_norm": 2.9896271228790283,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.3302,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.6274509803921569,
638
+ "grad_norm": 4.0551629066467285,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.3202,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.6345811051693404,
645
+ "grad_norm": 2.5737249851226807,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.2139,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.6417112299465241,
652
+ "grad_norm": 2.4582886695861816,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.2197,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.6488413547237076,
659
+ "grad_norm": 1.8644245862960815,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.1425,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.6559714795008913,
666
+ "grad_norm": 3.0225026607513428,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.1253,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.6631016042780749,
673
+ "grad_norm": 3.376275062561035,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.2162,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.6702317290552585,
680
+ "grad_norm": 3.654719591140747,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.2584,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6773618538324421,
687
+ "grad_norm": 1.9528889656066895,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.1685,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.6844919786096256,
694
+ "grad_norm": 1.6919232606887817,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0871,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.6916221033868093,
701
+ "grad_norm": 1.6383646726608276,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.2077,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.6987522281639929,
708
+ "grad_norm": 2.661104440689087,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.2855,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.7058823529411765,
715
+ "grad_norm": 2.2017295360565186,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.2031,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.7130124777183601,
722
+ "grad_norm": 2.1253581047058105,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.2846,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.7130124777183601,
729
+ "eval_loss": 0.3400123119354248,
730
+ "eval_runtime": 17.7933,
731
+ "eval_samples_per_second": 13.263,
732
+ "eval_steps_per_second": 3.316,
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