arcwarden46 commited on
Commit
8a9fee6
·
verified ·
1 Parent(s): 15687dd

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:cd26bd93b86c13408d81f23821427ea8c447fa2fb30b90925a31490131778ab5
3
  size 34456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6b2a52a799624bd3c86262a3788e12cf3a3e1ee68b2c0461e4ae6078f602526
3
  size 34456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19d8f8739a6d0eaa79836c7ac668b25119b15e531718dc0a0da9bcbafa72cfaa
3
  size 73222
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3dab4f657c248eaf6aa28c0ce667dff6e992c7e903da1625fcd2ab8517313ce
3
  size 73222
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4c1b1756c682c5c623bbdaae992f1be6852bd1ee3c08a74469b2de8b9630e8d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33822754786829181ceacca7455cdb5763d151a131b12e49ce524736226138f3
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": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.029394473838918283,
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": 195.718,
374
  "eval_steps_per_second": 48.981,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -387,7 +745,7 @@
387
  "early_stopping_threshold": 0.0
388
  },
389
  "attributes": {
390
- "early_stopping_patience_counter": 0
391
  }
392
  },
393
  "TrainerControl": {
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 9285756125184.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
  "best_metric": 11.5,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.058788947677836566,
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": 195.718,
374
  "eval_steps_per_second": 48.981,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.029982363315696647,
379
+ "grad_norm": 8.072692435234785e-05,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 46.0,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.030570252792475015,
386
+ "grad_norm": 6.423099694075063e-05,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 46.0,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.03115814226925338,
393
+ "grad_norm": 8.989491470856592e-05,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 46.0,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.031746031746031744,
400
+ "grad_norm": 7.5341529736761e-05,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 46.0,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03233392122281011,
407
+ "grad_norm": 8.537779649486765e-05,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 46.0,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03292181069958848,
414
+ "grad_norm": 6.623294757446274e-05,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 46.0,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03350970017636684,
421
+ "grad_norm": 9.374333603773266e-05,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 46.0,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.03409758965314521,
428
+ "grad_norm": 7.75801163399592e-05,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 46.0,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03468547912992358,
435
+ "grad_norm": 9.134270658250898e-05,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 46.0,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03527336860670194,
442
+ "grad_norm": 8.968768815975636e-05,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 46.0,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.035861258083480306,
449
+ "grad_norm": 0.0001133866753662005,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 46.0,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.036449147560258674,
456
+ "grad_norm": 0.00012280046939849854,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 46.0,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.037037037037037035,
463
+ "grad_norm": 0.00011304698273306713,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 46.0,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0376249265138154,
470
+ "grad_norm": 0.00010085060785058886,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 46.0,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.03821281599059377,
477
+ "grad_norm": 0.0001040530187310651,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 46.0,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.03880070546737213,
484
+ "grad_norm": 0.00011165401519974694,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 46.0,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.0393885949441505,
491
+ "grad_norm": 0.00010556532652117312,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 46.0,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.03997648442092887,
498
+ "grad_norm": 0.0001224667503265664,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 46.0,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.04056437389770723,
505
+ "grad_norm": 9.401813440490514e-05,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 46.0,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0411522633744856,
512
+ "grad_norm": 9.731772297527641e-05,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 46.0,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.041740152851263965,
519
+ "grad_norm": 0.0001305223850067705,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 46.0,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.042328042328042326,
526
+ "grad_norm": 0.00014116507372818887,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 46.0,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.042915931804820694,
533
+ "grad_norm": 0.00012054727994836867,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 46.0,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04350382128159906,
540
+ "grad_norm": 0.00012138788588345051,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 46.0,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04409171075837742,
547
+ "grad_norm": 0.00012971316755283624,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 46.0,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.04467960023515579,
554
+ "grad_norm": 0.00013737195695284754,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 46.0,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.04526748971193416,
561
+ "grad_norm": 0.0001315642730332911,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 46.0,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.04585537918871252,
568
+ "grad_norm": 0.00016319795395247638,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 46.0,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.04644326866549089,
575
+ "grad_norm": 0.00023923353001009673,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 46.0,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.047031158142269255,
582
+ "grad_norm": 0.00019476351735647768,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 46.0,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.047619047619047616,
589
+ "grad_norm": 0.00018909820937551558,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 46.0,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.048206937095825984,
596
+ "grad_norm": 0.0002272109704790637,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 46.0,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.04879482657260435,
603
+ "grad_norm": 0.00020458166545722634,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 46.0,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.04938271604938271,
610
+ "grad_norm": 0.00013996608322486281,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 46.0,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.04997060552616108,
617
+ "grad_norm": 0.00013861458864994347,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 46.0,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.05055849500293945,
624
+ "grad_norm": 0.0001646235177759081,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 46.0,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.05114638447971781,
631
+ "grad_norm": 0.0001694798847893253,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 46.0,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.05173427395649618,
638
+ "grad_norm": 0.00013206205039750785,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 46.0,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.052322163433274546,
645
+ "grad_norm": 0.00018996188009623438,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 46.0,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.05291005291005291,
652
+ "grad_norm": 0.00023221633455250412,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 46.0,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.053497942386831275,
659
+ "grad_norm": 0.0002046255103778094,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 46.0,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.05408583186360964,
666
+ "grad_norm": 0.0002309479023097083,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 46.0,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.054673721340388004,
673
+ "grad_norm": 0.0001794481504475698,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 46.0,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.05526161081716637,
680
+ "grad_norm": 0.0002424710983177647,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 46.0,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.05584950029394474,
687
+ "grad_norm": 0.00017888547154143453,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 46.0,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.0564373897707231,
694
+ "grad_norm": 0.000146155507536605,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 46.0,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.05702527924750147,
701
+ "grad_norm": 0.000218566317926161,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 46.0,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.05761316872427984,
708
+ "grad_norm": 0.00023672141833230853,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 46.0,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0582010582010582,
715
+ "grad_norm": 0.0001613728527445346,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 46.0,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.058788947677836566,
722
+ "grad_norm": 0.0003606592945288867,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 46.0,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.058788947677836566,
729
+ "eval_loss": 11.5,
730
+ "eval_runtime": 14.6648,
731
+ "eval_samples_per_second": 195.366,
732
+ "eval_steps_per_second": 48.893,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
745
  "early_stopping_threshold": 0.0
746
  },
747
  "attributes": {
748
+ "early_stopping_patience_counter": 1
749
  }
750
  },
751
  "TrainerControl": {
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 18531314171904.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null