cilooor commited on
Commit
fae74d7
·
verified ·
1 Parent(s): 6b16165

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:ec3ba720300643a0027e12cc6d1bfa0ddf5b74431bc2df76cf08d1f36d0889c3
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e94674495c060d58a1b74c9205c6b002c1b3a6ba3ace098c7e5580555da355a
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:280ec6ecbbcff1c029e135a8537381c23db8800370d0f88f2c9baae442cf4243
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee83da3cdbc377d4213520c4f199853dc662e6643c71576e41c75a0e02ec6a1
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dadf468976eaef76bac44aa555b02ab127a6a14ec9b59ab8b31b23359a75cc5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6ab49a62a76d626a212277e13b56a15da5e986df0305cc6df512f8924d90f3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f153938c08b62688f6e56c8abc0a37c00fee4d7e364e15e32c7b150f9f5f65c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b0f0591a54513981f9045153a7608f989005ce4fb6ed2c798b085bae23c1094
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.560448408126831,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.10256410256410256,
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": 58.086,
374
  "eval_steps_per_second": 14.557,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3864241215897600.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1515552997589111,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.20512820512820512,
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": 58.086,
374
  "eval_steps_per_second": 14.557,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.10461538461538461,
379
+ "grad_norm": 17.870498657226562,
380
+ "learning_rate": 8.004947754429507e-05,
381
+ "loss": 2.0845,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.10666666666666667,
386
+ "grad_norm": 12.60925006866455,
387
+ "learning_rate": 7.957804998855866e-05,
388
+ "loss": 1.7185,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.10871794871794872,
393
+ "grad_norm": 7.440306663513184,
394
+ "learning_rate": 7.909716913921508e-05,
395
+ "loss": 1.4469,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.11076923076923077,
400
+ "grad_norm": 4.980508804321289,
401
+ "learning_rate": 7.860696646428694e-05,
402
+ "loss": 1.385,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.11282051282051282,
407
+ "grad_norm": 6.349368572235107,
408
+ "learning_rate": 7.810757598029093e-05,
409
+ "loss": 1.327,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.11487179487179487,
414
+ "grad_norm": 5.48588228225708,
415
+ "learning_rate": 7.759913421559902e-05,
416
+ "loss": 1.2723,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.11692307692307692,
421
+ "grad_norm": 5.339735507965088,
422
+ "learning_rate": 7.708178017311287e-05,
423
+ "loss": 1.1835,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.11897435897435897,
428
+ "grad_norm": 4.799980163574219,
429
+ "learning_rate": 7.655565529226198e-05,
430
+ "loss": 1.3459,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.12102564102564102,
435
+ "grad_norm": 4.358178615570068,
436
+ "learning_rate": 7.602090341033547e-05,
437
+ "loss": 1.17,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.12307692307692308,
442
+ "grad_norm": 4.27966833114624,
443
+ "learning_rate": 7.547767072315837e-05,
444
+ "loss": 1.2933,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.12512820512820513,
449
+ "grad_norm": 3.893486499786377,
450
+ "learning_rate": 7.492610574512317e-05,
451
+ "loss": 1.0023,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.12717948717948718,
456
+ "grad_norm": 3.4954171180725098,
457
+ "learning_rate": 7.436635926858759e-05,
458
+ "loss": 1.0245,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.12923076923076923,
463
+ "grad_norm": 4.20940637588501,
464
+ "learning_rate": 7.379858432264925e-05,
465
+ "loss": 1.3105,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.13128205128205128,
470
+ "grad_norm": 3.732714891433716,
471
+ "learning_rate": 7.322293613130917e-05,
472
+ "loss": 1.1955,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.13333333333333333,
477
+ "grad_norm": 4.190236568450928,
478
+ "learning_rate": 7.263957207103507e-05,
479
+ "loss": 1.2116,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.13538461538461538,
484
+ "grad_norm": 4.6758713722229,
485
+ "learning_rate": 7.204865162773613e-05,
486
+ "loss": 1.2503,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.13743589743589743,
491
+ "grad_norm": 4.13181209564209,
492
+ "learning_rate": 7.14503363531613e-05,
493
+ "loss": 1.2816,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.13948717948717948,
498
+ "grad_norm": 4.117213726043701,
499
+ "learning_rate": 7.084478982073247e-05,
500
+ "loss": 1.1853,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.14153846153846153,
505
+ "grad_norm": 3.732710599899292,
506
+ "learning_rate": 7.023217758082528e-05,
507
+ "loss": 1.1477,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.14358974358974358,
512
+ "grad_norm": 3.815847396850586,
513
+ "learning_rate": 6.961266711550922e-05,
514
+ "loss": 0.984,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.14564102564102563,
519
+ "grad_norm": 5.187172889709473,
520
+ "learning_rate": 6.898642779275972e-05,
521
+ "loss": 1.3038,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.1476923076923077,
526
+ "grad_norm": 4.535514831542969,
527
+ "learning_rate": 6.835363082015469e-05,
528
+ "loss": 1.12,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.14974358974358976,
533
+ "grad_norm": 4.647159099578857,
534
+ "learning_rate": 6.771444919806798e-05,
535
+ "loss": 0.9245,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.1517948717948718,
540
+ "grad_norm": 3.8211467266082764,
541
+ "learning_rate": 6.706905767237288e-05,
542
+ "loss": 0.888,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.15384615384615385,
547
+ "grad_norm": 4.1535725593566895,
548
+ "learning_rate": 6.641763268666833e-05,
549
+ "loss": 1.1647,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.1558974358974359,
554
+ "grad_norm": 4.298352241516113,
555
+ "learning_rate": 6.576035233404096e-05,
556
+ "loss": 0.8633,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.15794871794871795,
561
+ "grad_norm": 4.210323810577393,
562
+ "learning_rate": 6.509739630837631e-05,
563
+ "loss": 1.101,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.16,
568
+ "grad_norm": 4.263596057891846,
569
+ "learning_rate": 6.442894585523218e-05,
570
+ "loss": 0.9679,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.16205128205128205,
575
+ "grad_norm": 4.171397686004639,
576
+ "learning_rate": 6.375518372228808e-05,
577
+ "loss": 0.9602,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.1641025641025641,
582
+ "grad_norm": 4.652695655822754,
583
+ "learning_rate": 6.307629410938363e-05,
584
+ "loss": 0.9892,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.16615384615384615,
589
+ "grad_norm": 4.602456092834473,
590
+ "learning_rate": 6.239246261816035e-05,
591
+ "loss": 1.0068,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1682051282051282,
596
+ "grad_norm": 4.614451885223389,
597
+ "learning_rate": 6.170387620131993e-05,
598
+ "loss": 1.0347,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.17025641025641025,
603
+ "grad_norm": 6.362389087677002,
604
+ "learning_rate": 6.101072311151325e-05,
605
+ "loss": 0.8976,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.1723076923076923,
610
+ "grad_norm": 4.6694254875183105,
611
+ "learning_rate": 6.0313192849873945e-05,
612
+ "loss": 0.8724,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.17435897435897435,
617
+ "grad_norm": 4.3068013191223145,
618
+ "learning_rate": 5.961147611421077e-05,
619
+ "loss": 0.8245,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1764102564102564,
624
+ "grad_norm": 3.9519715309143066,
625
+ "learning_rate": 5.890576474687264e-05,
626
+ "loss": 0.9099,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.17846153846153845,
631
+ "grad_norm": 4.506985187530518,
632
+ "learning_rate": 5.8196251682300926e-05,
633
+ "loss": 1.1025,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.18051282051282053,
638
+ "grad_norm": 5.209732532501221,
639
+ "learning_rate": 5.748313089428301e-05,
640
+ "loss": 0.9199,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.18256410256410258,
645
+ "grad_norm": 5.635715484619141,
646
+ "learning_rate": 5.676659734292189e-05,
647
+ "loss": 0.8316,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.18461538461538463,
652
+ "grad_norm": 6.903309345245361,
653
+ "learning_rate": 5.604684692133597e-05,
654
+ "loss": 1.2001,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.18666666666666668,
659
+ "grad_norm": 5.074714660644531,
660
+ "learning_rate": 5.532407640210383e-05,
661
+ "loss": 1.0546,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.18871794871794872,
666
+ "grad_norm": 5.425539970397949,
667
+ "learning_rate": 5.4598483383468616e-05,
668
+ "loss": 1.0701,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.19076923076923077,
673
+ "grad_norm": 5.213406562805176,
674
+ "learning_rate": 5.3870266235316614e-05,
675
+ "loss": 1.1455,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.19282051282051282,
680
+ "grad_norm": 5.347712516784668,
681
+ "learning_rate": 5.313962404494496e-05,
682
+ "loss": 1.0502,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.19487179487179487,
687
+ "grad_norm": 6.263542652130127,
688
+ "learning_rate": 5.240675656263303e-05,
689
+ "loss": 1.1716,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.19692307692307692,
694
+ "grad_norm": 6.650071620941162,
695
+ "learning_rate": 5.167186414703289e-05,
696
+ "loss": 1.1502,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.19897435897435897,
701
+ "grad_norm": 6.575021743774414,
702
+ "learning_rate": 5.093514771039311e-05,
703
+ "loss": 1.0757,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.20102564102564102,
708
+ "grad_norm": 6.4250640869140625,
709
+ "learning_rate": 5.019680866363139e-05,
710
+ "loss": 1.1983,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.20307692307692307,
715
+ "grad_norm": 8.973063468933105,
716
+ "learning_rate": 4.9457048861270835e-05,
717
+ "loss": 1.8378,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.20512820512820512,
722
+ "grad_norm": 24.881746292114258,
723
+ "learning_rate": 4.871607054625497e-05,
724
+ "loss": 3.2016,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.20512820512820512,
729
+ "eval_loss": 1.1515552997589111,
730
+ "eval_runtime": 14.17,
731
+ "eval_samples_per_second": 58.01,
732
+ "eval_steps_per_second": 14.538,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7728482431795200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null