aleegis10 commited on
Commit
f627d84
·
verified ·
1 Parent(s): 9ced0f1

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 sha256:57c21359898fd2d19224401514f3c3e2be115cc3e667331432377885fd7f0682
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bdbe20707d5573de72492b5b52f643c38882423895821ba9ec529b13249754
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89a761e176a5346c5136a6a4147a628260d2a8a3ac3f7491779df0ea85adc69c
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:932c117ce6046b17e536cdfefaabe538916cb836d6b91b5274aea4cf7bba5fb7
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d95e30fcc53f67298a6f2f62fcecd31ddb646bb907fe8df80af18c21cb69c5c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f003676a6cbf38418e7c7d43282c9aa1379d9623a39594d18b7f56bd6bb4c309
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": 0.2936895191669464,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.011852554225435581,
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": 13.705,
374
  "eval_steps_per_second": 3.428,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.190764995162931e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.28296175599098206,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.023705108450871162,
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": 13.705,
374
  "eval_steps_per_second": 3.428,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.012089605309944292,
379
+ "grad_norm": 9.533975601196289,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.2758,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.012326656394453005,
386
+ "grad_norm": 10.313169479370117,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.0634,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.012563707478961716,
393
+ "grad_norm": 10.298772811889648,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.292,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.012800758563470427,
400
+ "grad_norm": 7.554491996765137,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.1744,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.01303780964797914,
407
+ "grad_norm": 11.438995361328125,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.545,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.013274860732487851,
414
+ "grad_norm": 9.73892879486084,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.3023,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.013511911816996562,
421
+ "grad_norm": 7.812572956085205,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.3008,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.013748962901505275,
428
+ "grad_norm": 9.590088844299316,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.5249,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.013986013986013986,
435
+ "grad_norm": 9.948052406311035,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.3549,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.014223065070522697,
442
+ "grad_norm": 8.376433372497559,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.2803,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.01446011615503141,
449
+ "grad_norm": 5.502856254577637,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.9784,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.014697167239540121,
456
+ "grad_norm": 9.21668815612793,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.4134,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.014934218324048832,
463
+ "grad_norm": 6.221367835998535,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.979,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.015171269408557545,
470
+ "grad_norm": 9.170941352844238,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.1757,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.015408320493066256,
477
+ "grad_norm": 7.874046802520752,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.0453,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.01564537157757497,
484
+ "grad_norm": 9.328206062316895,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.1295,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.01588242266208368,
491
+ "grad_norm": 10.148048400878906,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.8948,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.01611947374659239,
498
+ "grad_norm": 10.749184608459473,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.6974,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.016356524831101102,
505
+ "grad_norm": 11.889942169189453,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.4894,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.016593575915609813,
512
+ "grad_norm": 11.449923515319824,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.3378,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.016830627000118524,
519
+ "grad_norm": 7.078919410705566,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.9582,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.01706767808462724,
526
+ "grad_norm": 9.08558177947998,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.7153,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.01730472916913595,
533
+ "grad_norm": 8.467891693115234,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.3214,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01754178025364466,
540
+ "grad_norm": 10.016956329345703,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.3502,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.017778831338153372,
547
+ "grad_norm": 8.021065711975098,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.1391,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.018015882422662083,
554
+ "grad_norm": 10.226483345031738,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.2666,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.018252933507170794,
561
+ "grad_norm": 7.5994672775268555,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.929,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.01848998459167951,
568
+ "grad_norm": 11.9320650100708,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.8044,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01872703567618822,
575
+ "grad_norm": 9.507772445678711,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.9235,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.01896408676069693,
582
+ "grad_norm": 8.77246379852295,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.0449,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.01920113784520564,
589
+ "grad_norm": 11.77663803100586,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.0512,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.019438188929714353,
596
+ "grad_norm": 10.001542091369629,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.2113,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.019675240014223064,
603
+ "grad_norm": 9.057281494140625,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.1445,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.01991229109873178,
610
+ "grad_norm": 18.364543914794922,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.159,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.02014934218324049,
617
+ "grad_norm": 9.89426326751709,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.9635,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0203863932677492,
624
+ "grad_norm": 12.017746925354004,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.0893,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02062344435225791,
631
+ "grad_norm": 11.03870964050293,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.8324,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.020860495436766623,
638
+ "grad_norm": 10.81103515625,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.472,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.021097546521275334,
645
+ "grad_norm": 27.316665649414062,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.0544,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.021334597605784045,
652
+ "grad_norm": 20.078157424926758,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.8053,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.02157164869029276,
659
+ "grad_norm": 9.962789535522461,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.0016,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.02180869977480147,
666
+ "grad_norm": 17.85474967956543,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.117,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.02204575085931018,
673
+ "grad_norm": 15.2191162109375,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.0432,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.022282801943818892,
680
+ "grad_norm": 28.267955780029297,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.8571,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.022519853028327604,
687
+ "grad_norm": 6.8763108253479,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.6518,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.022756904112836315,
694
+ "grad_norm": 8.670818328857422,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.9891,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.02299395519734503,
701
+ "grad_norm": 9.819561958312988,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.4,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.02323100628185374,
708
+ "grad_norm": 7.537906169891357,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.0282,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.02346805736636245,
715
+ "grad_norm": 17.41543960571289,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.2158,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.023705108450871162,
722
+ "grad_norm": 9.822668075561523,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.0042,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.023705108450871162,
729
+ "eval_loss": 0.28296175599098206,
730
+ "eval_runtime": 516.2865,
731
+ "eval_samples_per_second": 13.762,
732
+ "eval_steps_per_second": 3.442,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4345755040101171e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null