bbytxt commited on
Commit
d6b0548
·
verified ·
1 Parent(s): 5fa6a0b

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:dfc694fb1ed22297e8fa2de26a8103fa8862fbf06dd698b77fb85ebd765e3101
3
  size 100690288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1bd4b20d094f878ef6106c6cb8bd5bb7cf0902d3912b21cb0fd117680dbb7f6
3
  size 100690288
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5974934d0e459322d70c43e89de2860e9ae2ae56886d72304db2d3b4a5b3b456
3
  size 201488570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9ccb993cbdef2f47caf3524427390a5716422f4d6d18a4479b389d36df2b4e0
3
  size 201488570
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad85e695a5ec576dfd9db3ebddb9c1e3e53504c1ab5559b59ea7a43d9e15f829
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bd9bd224b07d61ed878e6e03bc9ff1b78e18ab9e1cdc52835e5502e8d383cda
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.210021734237671,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.033818058843422386,
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": 41.485,
374
  "eval_steps_per_second": 5.198,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3235348733755392.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.126096248626709,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06763611768684477,
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": 41.485,
374
  "eval_steps_per_second": 5.198,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.034494420020290836,
379
+ "grad_norm": 4.682622909545898,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 7.3033,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03517078119715928,
386
+ "grad_norm": 4.259825706481934,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 8.2038,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.03584714237402773,
393
+ "grad_norm": 3.8585610389709473,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 8.0316,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03652350355089618,
400
+ "grad_norm": 4.340334415435791,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 8.1593,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.037199864727764625,
407
+ "grad_norm": 3.958160877227783,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 8.2496,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.037876225904633076,
414
+ "grad_norm": 3.8694088459014893,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 8.4785,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03855258708150152,
421
+ "grad_norm": 3.9794576168060303,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 8.4423,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.03922894825836997,
428
+ "grad_norm": 3.9265565872192383,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 8.4504,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.039905309435238415,
435
+ "grad_norm": 4.041325092315674,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 8.3756,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.040581670612106865,
442
+ "grad_norm": 5.280641078948975,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 8.1592,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.041258031788975316,
449
+ "grad_norm": 3.9607338905334473,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 8.0258,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04193439296584376,
456
+ "grad_norm": 4.460994243621826,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 8.5226,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04261075414271221,
463
+ "grad_norm": 4.187047004699707,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 8.3819,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.043287115319580655,
470
+ "grad_norm": 3.973010540008545,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 8.2575,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.043963476496449105,
477
+ "grad_norm": 4.07871675491333,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 8.3387,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04463983767331755,
484
+ "grad_norm": 4.1719746589660645,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 8.362,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.045316198850186,
491
+ "grad_norm": 3.8811497688293457,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 7.6999,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.045992560027054444,
498
+ "grad_norm": 6.439735412597656,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 8.0578,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.046668921203922895,
505
+ "grad_norm": 5.49559211730957,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 8.1918,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.047345282380791345,
512
+ "grad_norm": 4.034685134887695,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 8.1877,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04802164355765979,
519
+ "grad_norm": 4.29405403137207,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 7.9481,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04869800473452824,
526
+ "grad_norm": 4.201921463012695,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 8.6197,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.049374365911396684,
533
+ "grad_norm": 4.181796073913574,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 8.3492,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.050050727088265135,
540
+ "grad_norm": 6.746152877807617,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 8.3253,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.05072708826513358,
547
+ "grad_norm": 7.181731224060059,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 8.5496,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.05140344944200203,
554
+ "grad_norm": 6.340611457824707,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 8.6001,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.05207981061887048,
561
+ "grad_norm": 4.404982089996338,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 8.7198,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.052756171795738924,
568
+ "grad_norm": 4.475285053253174,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 8.6514,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.053432532972607374,
575
+ "grad_norm": 4.532863616943359,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 8.775,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05410889414947582,
582
+ "grad_norm": 4.5660858154296875,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 8.9584,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05478525532634427,
589
+ "grad_norm": 4.7173752784729,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 8.2346,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.05546161650321271,
596
+ "grad_norm": 4.502657413482666,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 8.7028,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.056137977680081164,
603
+ "grad_norm": 4.612180233001709,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 8.6685,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.056814338856949614,
610
+ "grad_norm": 4.754201412200928,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 8.7271,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.05749070003381806,
617
+ "grad_norm": 4.44357967376709,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 8.5977,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.05816706121068651,
624
+ "grad_norm": 4.550760746002197,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 8.8932,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.05884342238755495,
631
+ "grad_norm": 4.751630783081055,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 9.1663,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.059519783564423404,
638
+ "grad_norm": 5.078840255737305,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 8.8868,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.06019614474129185,
645
+ "grad_norm": 5.119762897491455,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 8.6316,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0608725059181603,
652
+ "grad_norm": 5.111042499542236,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 8.5512,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.06154886709502874,
659
+ "grad_norm": 5.240387916564941,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 8.7123,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.06222522827189719,
666
+ "grad_norm": 4.964595794677734,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 8.6408,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06290158944876564,
673
+ "grad_norm": 5.38602876663208,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 9.1276,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0635779506256341,
680
+ "grad_norm": 5.626663684844971,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 8.7763,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.06425431180250253,
687
+ "grad_norm": 5.479903221130371,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 8.9741,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.06493067297937098,
694
+ "grad_norm": 5.873063564300537,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 9.427,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06560703415623943,
701
+ "grad_norm": 5.906656742095947,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 9.2991,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.06628339533310788,
708
+ "grad_norm": 6.124764442443848,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 9.0502,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.06695975650997633,
715
+ "grad_norm": 6.487301826477051,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 9.3022,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06763611768684477,
722
+ "grad_norm": 8.364432334899902,
723
+ "learning_rate": 0.0,
724
+ "loss": 9.5886,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06763611768684477,
729
+ "eval_loss": 2.126096248626709,
730
+ "eval_runtime": 60.029,
731
+ "eval_samples_per_second": 41.48,
732
+ "eval_steps_per_second": 5.197,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6454601205153792.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null