lesso commited on
Commit
cb97c09
·
verified ·
1 Parent(s): 77dca06

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 sha256:5fe2bc7f410b18f2d84da57aee6a426601b74ac3145a9f8f5b999f3b26397ce8
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6809709cc6e0b32acb814a9eb2ea10485e2e30a7abfc2c9b4b635a04a03b642
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3c3a3075b7c67c1ec552e99862e9a6ab02259ff2efd56545d08d9a528992115
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fc0b6e6a51ab504fa5b81fae3661f568391ff25aeb91ed011f92a1a5964026e
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a021a67ea182c2e6e2e77b7f247ec4b54190e2f7f54d32161d3ce4005a4cba3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e2bf3019df065cb5a9f9969cad64bcd1e961e034fab484e16358f1afda784b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcbe1ba74b58330afa49026b3467516d09bde409f813ca3b749b16b9edb36df4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ab3d2b0401484126213dd055d9044edf00d7b06db4fe9dbad6027ee8b5d34b1
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.573653221130371,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.03762227238525207,
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": 14.886,
374
  "eval_steps_per_second": 3.721,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.8066349863469056e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.492374897003174,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.07524454477050414,
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": 14.886,
374
  "eval_steps_per_second": 3.721,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03837471783295711,
379
+ "grad_norm": 6.201414108276367,
380
+ "learning_rate": 7.983263157894736e-05,
381
+ "loss": 4.6951,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03912716328066215,
386
+ "grad_norm": 4.830835342407227,
387
+ "learning_rate": 7.929684210526315e-05,
388
+ "loss": 5.02,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0398796087283672,
393
+ "grad_norm": 7.732100009918213,
394
+ "learning_rate": 7.876105263157895e-05,
395
+ "loss": 4.9632,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.040632054176072234,
400
+ "grad_norm": 7.422882556915283,
401
+ "learning_rate": 7.822526315789473e-05,
402
+ "loss": 4.2894,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.04138449962377728,
407
+ "grad_norm": 6.019810676574707,
408
+ "learning_rate": 7.768947368421053e-05,
409
+ "loss": 4.5985,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.042136945071482315,
414
+ "grad_norm": 7.448675632476807,
415
+ "learning_rate": 7.715368421052631e-05,
416
+ "loss": 5.6458,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.04288939051918736,
421
+ "grad_norm": 6.525016784667969,
422
+ "learning_rate": 7.66178947368421e-05,
423
+ "loss": 4.4928,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0436418359668924,
428
+ "grad_norm": 5.862019062042236,
429
+ "learning_rate": 7.608210526315788e-05,
430
+ "loss": 5.0442,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.04439428141459744,
435
+ "grad_norm": 6.698094844818115,
436
+ "learning_rate": 7.554631578947368e-05,
437
+ "loss": 5.1862,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.045146726862302484,
442
+ "grad_norm": 5.901148796081543,
443
+ "learning_rate": 7.501052631578947e-05,
444
+ "loss": 4.6401,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.04589917231000752,
449
+ "grad_norm": 8.506747245788574,
450
+ "learning_rate": 7.447473684210527e-05,
451
+ "loss": 5.6167,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.046651617757712566,
456
+ "grad_norm": 8.143284797668457,
457
+ "learning_rate": 7.393894736842105e-05,
458
+ "loss": 4.5655,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04740406320541761,
463
+ "grad_norm": 5.302389621734619,
464
+ "learning_rate": 7.340315789473684e-05,
465
+ "loss": 4.4897,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.04815650865312265,
470
+ "grad_norm": 5.529751300811768,
471
+ "learning_rate": 7.286736842105262e-05,
472
+ "loss": 4.2722,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04890895410082769,
477
+ "grad_norm": 8.762489318847656,
478
+ "learning_rate": 7.233157894736842e-05,
479
+ "loss": 5.1436,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04966139954853273,
484
+ "grad_norm": 11.295607566833496,
485
+ "learning_rate": 7.179578947368421e-05,
486
+ "loss": 4.9496,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.05041384499623777,
491
+ "grad_norm": 9.971809387207031,
492
+ "learning_rate": 7.125999999999999e-05,
493
+ "loss": 5.4893,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.051166290443942816,
498
+ "grad_norm": 7.344180583953857,
499
+ "learning_rate": 7.072421052631579e-05,
500
+ "loss": 4.6742,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.05191873589164785,
505
+ "grad_norm": 9.844782829284668,
506
+ "learning_rate": 7.018842105263158e-05,
507
+ "loss": 5.1691,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.0526711813393529,
512
+ "grad_norm": 8.95771598815918,
513
+ "learning_rate": 6.965263157894736e-05,
514
+ "loss": 4.879,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.05342362678705794,
519
+ "grad_norm": 8.04973030090332,
520
+ "learning_rate": 6.911684210526316e-05,
521
+ "loss": 5.0598,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.05417607223476298,
526
+ "grad_norm": 8.579294204711914,
527
+ "learning_rate": 6.858105263157894e-05,
528
+ "loss": 4.8055,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.05492851768246802,
533
+ "grad_norm": 7.308038234710693,
534
+ "learning_rate": 6.804526315789473e-05,
535
+ "loss": 4.7293,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.05568096313017306,
540
+ "grad_norm": 7.7795233726501465,
541
+ "learning_rate": 6.750947368421052e-05,
542
+ "loss": 5.0379,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.056433408577878104,
547
+ "grad_norm": 8.343374252319336,
548
+ "learning_rate": 6.697368421052631e-05,
549
+ "loss": 4.4904,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.05718585402558315,
554
+ "grad_norm": 7.44524621963501,
555
+ "learning_rate": 6.64378947368421e-05,
556
+ "loss": 4.7685,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.057938299473288185,
561
+ "grad_norm": 10.718270301818848,
562
+ "learning_rate": 6.59021052631579e-05,
563
+ "loss": 5.2094,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.05869074492099323,
568
+ "grad_norm": 9.407214164733887,
569
+ "learning_rate": 6.536631578947368e-05,
570
+ "loss": 5.0866,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.059443190368698266,
575
+ "grad_norm": 8.373135566711426,
576
+ "learning_rate": 6.483052631578947e-05,
577
+ "loss": 4.8998,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.06019563581640331,
582
+ "grad_norm": 8.654524803161621,
583
+ "learning_rate": 6.429473684210525e-05,
584
+ "loss": 4.6364,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.060948081264108354,
589
+ "grad_norm": 9.621380805969238,
590
+ "learning_rate": 6.375894736842104e-05,
591
+ "loss": 5.1948,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.06170052671181339,
596
+ "grad_norm": 13.150786399841309,
597
+ "learning_rate": 6.322315789473684e-05,
598
+ "loss": 5.4827,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.062452972159518436,
603
+ "grad_norm": 10.533498764038086,
604
+ "learning_rate": 6.268736842105264e-05,
605
+ "loss": 4.9195,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.06320541760722348,
610
+ "grad_norm": 10.708104133605957,
611
+ "learning_rate": 6.215157894736842e-05,
612
+ "loss": 4.8833,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.06395786305492852,
617
+ "grad_norm": 7.892517566680908,
618
+ "learning_rate": 6.16157894736842e-05,
619
+ "loss": 5.0272,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.06471030850263355,
624
+ "grad_norm": 13.007377624511719,
625
+ "learning_rate": 6.107999999999999e-05,
626
+ "loss": 4.8137,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.0654627539503386,
631
+ "grad_norm": 11.001848220825195,
632
+ "learning_rate": 6.054421052631578e-05,
633
+ "loss": 5.8105,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.06621519939804364,
638
+ "grad_norm": 13.360245704650879,
639
+ "learning_rate": 6.000842105263157e-05,
640
+ "loss": 5.2308,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.06696764484574869,
645
+ "grad_norm": 8.78776741027832,
646
+ "learning_rate": 5.947263157894737e-05,
647
+ "loss": 4.3293,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.06772009029345373,
652
+ "grad_norm": 11.788161277770996,
653
+ "learning_rate": 5.893684210526316e-05,
654
+ "loss": 5.5094,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.06847253574115876,
659
+ "grad_norm": 13.817206382751465,
660
+ "learning_rate": 5.8401052631578944e-05,
661
+ "loss": 5.6535,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0692249811888638,
666
+ "grad_norm": 10.35663890838623,
667
+ "learning_rate": 5.7865263157894736e-05,
668
+ "loss": 4.9656,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06997742663656885,
673
+ "grad_norm": 12.754554748535156,
674
+ "learning_rate": 5.732947368421052e-05,
675
+ "loss": 6.037,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.07072987208427389,
680
+ "grad_norm": 13.788698196411133,
681
+ "learning_rate": 5.6793684210526306e-05,
682
+ "loss": 5.4732,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.07148231753197894,
687
+ "grad_norm": 10.369476318359375,
688
+ "learning_rate": 5.6257894736842105e-05,
689
+ "loss": 4.9698,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.07223476297968397,
694
+ "grad_norm": 11.039383888244629,
695
+ "learning_rate": 5.57221052631579e-05,
696
+ "loss": 5.0991,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.07298720842738901,
701
+ "grad_norm": 18.217975616455078,
702
+ "learning_rate": 5.518631578947368e-05,
703
+ "loss": 5.7764,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.07373965387509406,
708
+ "grad_norm": 13.361612319946289,
709
+ "learning_rate": 5.4650526315789474e-05,
710
+ "loss": 4.8924,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0744920993227991,
715
+ "grad_norm": 24.20296287536621,
716
+ "learning_rate": 5.411473684210526e-05,
717
+ "loss": 6.2003,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.07524454477050414,
722
+ "grad_norm": 16.34416389465332,
723
+ "learning_rate": 5.3578947368421044e-05,
724
+ "loss": 5.3467,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.07524454477050414,
729
+ "eval_loss": 2.492374897003174,
730
+ "eval_runtime": 37.6751,
731
+ "eval_samples_per_second": 14.864,
732
+ "eval_steps_per_second": 3.716,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.613269972693811e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null