prxy5606 commited on
Commit
50e10a6
·
verified ·
1 Parent(s): fe46b97

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:e8e23203049c5d18063f2a635c872379448686ef927b9481255e2fc3aaac1b50
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70097065aaee7cce2f51c4d8c00e10116135a823af02692b44082a823a1dd1ec
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cf066c18e340875252a50addf2bf6671957204750c25b0152c1dd4ef1247dad
3
  size 1342555602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f205e6c2aa483c3ffb51c9a819942b6d288d13882a8bcd3e9b205a976177f7ce
3
  size 1342555602
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9cb139bc76f1ac9762675e942777eeba992825192e47b629184dfcd772f640a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0daf361b742a94c3f89fb07a30f370fad356787507ba63c4649ec31f20c12b5c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ece3236edcb393fe9fe067fb4c27aaaf2d1a125595517cb84b2456d9b62475c0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5429913997650146,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.009394964299135663,
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": 10.82,
374
  "eval_steps_per_second": 5.41,
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": 8.442888253027123e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2692981958389282,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.018789928598271326,
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": 10.82,
374
  "eval_steps_per_second": 5.41,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.009582863585118376,
379
+ "grad_norm": 12.12710189819336,
380
+ "learning_rate": 7.938926261462366e-05,
381
+ "loss": 4.1207,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.00977076287110109,
386
+ "grad_norm": 6.877650260925293,
387
+ "learning_rate": 7.754484907260513e-05,
388
+ "loss": 3.854,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.009958662157083803,
393
+ "grad_norm": 3.922449827194214,
394
+ "learning_rate": 7.564496387029532e-05,
395
+ "loss": 3.875,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.010146561443066516,
400
+ "grad_norm": 2.6158945560455322,
401
+ "learning_rate": 7.369343312364993e-05,
402
+ "loss": 3.8383,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.01033446072904923,
407
+ "grad_norm": 2.6309781074523926,
408
+ "learning_rate": 7.169418695587791e-05,
409
+ "loss": 3.3104,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.010522360015031942,
414
+ "grad_norm": 2.4806551933288574,
415
+ "learning_rate": 6.965125158269619e-05,
416
+ "loss": 3.6959,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.010710259301014656,
421
+ "grad_norm": 2.6647136211395264,
422
+ "learning_rate": 6.756874120406714e-05,
423
+ "loss": 4.4607,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.010898158586997369,
428
+ "grad_norm": 2.6696109771728516,
429
+ "learning_rate": 6.545084971874738e-05,
430
+ "loss": 5.5749,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.011086057872980082,
435
+ "grad_norm": 2.808939218521118,
436
+ "learning_rate": 6.330184227833376e-05,
437
+ "loss": 4.7221,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.011273957158962795,
442
+ "grad_norm": 2.9471914768218994,
443
+ "learning_rate": 6.112604669781572e-05,
444
+ "loss": 4.6405,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.011461856444945509,
449
+ "grad_norm": 2.7732815742492676,
450
+ "learning_rate": 5.8927844739931834e-05,
451
+ "loss": 4.311,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.011649755730928222,
456
+ "grad_norm": 2.873124599456787,
457
+ "learning_rate": 5.6711663290882776e-05,
458
+ "loss": 4.8382,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.011837655016910935,
463
+ "grad_norm": 2.967327117919922,
464
+ "learning_rate": 5.448196544517168e-05,
465
+ "loss": 4.4859,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.012025554302893648,
470
+ "grad_norm": 3.0220985412597656,
471
+ "learning_rate": 5.2243241517525754e-05,
472
+ "loss": 4.8879,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.012213453588876362,
477
+ "grad_norm": 5.608536720275879,
478
+ "learning_rate": 5e-05,
479
+ "loss": 4.8269,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.012401352874859075,
484
+ "grad_norm": 2.988602876663208,
485
+ "learning_rate": 4.775675848247427e-05,
486
+ "loss": 5.6113,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.012589252160841788,
491
+ "grad_norm": 2.927661180496216,
492
+ "learning_rate": 4.551803455482833e-05,
493
+ "loss": 4.4028,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.012777151446824501,
498
+ "grad_norm": 2.921163320541382,
499
+ "learning_rate": 4.328833670911724e-05,
500
+ "loss": 4.3565,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.012965050732807215,
505
+ "grad_norm": 3.0370848178863525,
506
+ "learning_rate": 4.107215526006817e-05,
507
+ "loss": 4.7969,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.013152950018789928,
512
+ "grad_norm": 3.3245177268981934,
513
+ "learning_rate": 3.887395330218429e-05,
514
+ "loss": 5.602,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.013340849304772641,
519
+ "grad_norm": 3.5475261211395264,
520
+ "learning_rate": 3.6698157721666246e-05,
521
+ "loss": 4.6884,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.013528748590755355,
526
+ "grad_norm": 3.5381057262420654,
527
+ "learning_rate": 3.4549150281252636e-05,
528
+ "loss": 5.7957,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.013716647876738068,
533
+ "grad_norm": 4.085561752319336,
534
+ "learning_rate": 3.243125879593286e-05,
535
+ "loss": 5.4665,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.013904547162720781,
540
+ "grad_norm": 4.82763671875,
541
+ "learning_rate": 3.0348748417303823e-05,
542
+ "loss": 5.9452,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.014092446448703494,
547
+ "grad_norm": 4.237555980682373,
548
+ "learning_rate": 2.8305813044122097e-05,
549
+ "loss": 5.4789,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.014280345734686208,
554
+ "grad_norm": 4.894902229309082,
555
+ "learning_rate": 2.630656687635007e-05,
556
+ "loss": 6.3016,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.01446824502066892,
561
+ "grad_norm": 4.798618316650391,
562
+ "learning_rate": 2.43550361297047e-05,
563
+ "loss": 5.9612,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.014656144306651634,
568
+ "grad_norm": 7.736368179321289,
569
+ "learning_rate": 2.245515092739488e-05,
570
+ "loss": 6.1193,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.014844043592634347,
575
+ "grad_norm": 5.555391788482666,
576
+ "learning_rate": 2.061073738537635e-05,
577
+ "loss": 6.2544,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.01503194287861706,
582
+ "grad_norm": 6.320089817047119,
583
+ "learning_rate": 1.8825509907063327e-05,
584
+ "loss": 5.6853,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.015219842164599774,
589
+ "grad_norm": 5.559424877166748,
590
+ "learning_rate": 1.7103063703014372e-05,
591
+ "loss": 4.8867,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.015407741450582487,
596
+ "grad_norm": 5.159763813018799,
597
+ "learning_rate": 1.544686755065677e-05,
598
+ "loss": 5.3778,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.0155956407365652,
603
+ "grad_norm": 5.190471649169922,
604
+ "learning_rate": 1.3860256808630428e-05,
605
+ "loss": 4.3495,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.015783540022547914,
610
+ "grad_norm": 5.162275314331055,
611
+ "learning_rate": 1.2346426699819458e-05,
612
+ "loss": 4.7606,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.01597143930853063,
617
+ "grad_norm": 5.0200347900390625,
618
+ "learning_rate": 1.090842587659851e-05,
619
+ "loss": 3.9641,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.01615933859451334,
624
+ "grad_norm": 4.721124172210693,
625
+ "learning_rate": 9.549150281252633e-06,
626
+ "loss": 3.9436,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.016347237880496055,
631
+ "grad_norm": 5.321893215179443,
632
+ "learning_rate": 8.271337313934869e-06,
633
+ "loss": 4.0494,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.016535137166478767,
638
+ "grad_norm": 5.561007022857666,
639
+ "learning_rate": 7.077560319906695e-06,
640
+ "loss": 4.481,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.01672303645246148,
645
+ "grad_norm": 6.137837886810303,
646
+ "learning_rate": 5.9702234071631e-06,
647
+ "loss": 4.0547,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.016910935738444193,
652
+ "grad_norm": 6.851164817810059,
653
+ "learning_rate": 4.951556604879048e-06,
654
+ "loss": 5.9195,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.017098835024426908,
659
+ "grad_norm": 6.387176036834717,
660
+ "learning_rate": 4.023611372427471e-06,
661
+ "loss": 6.3249,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.01728673431040962,
666
+ "grad_norm": 8.208516120910645,
667
+ "learning_rate": 3.18825646801314e-06,
668
+ "loss": 7.7682,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.017474633596392335,
673
+ "grad_norm": 8.880036354064941,
674
+ "learning_rate": 2.4471741852423237e-06,
675
+ "loss": 7.4679,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.017662532882375046,
680
+ "grad_norm": 9.490116119384766,
681
+ "learning_rate": 1.8018569652073381e-06,
682
+ "loss": 6.5789,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01785043216835776,
687
+ "grad_norm": 10.559647560119629,
688
+ "learning_rate": 1.2536043909088191e-06,
689
+ "loss": 7.196,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.018038331454340473,
694
+ "grad_norm": 10.684134483337402,
695
+ "learning_rate": 8.035205700685167e-07,
696
+ "loss": 5.8043,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.018226230740323188,
701
+ "grad_norm": 9.896649360656738,
702
+ "learning_rate": 4.52511911603265e-07,
703
+ "loss": 5.7818,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0184141300263059,
708
+ "grad_norm": 10.521429061889648,
709
+ "learning_rate": 2.012853002380466e-07,
710
+ "loss": 5.4138,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.018602029312288614,
715
+ "grad_norm": 12.07073974609375,
716
+ "learning_rate": 5.0346672934270534e-08,
717
+ "loss": 5.933,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.018789928598271326,
722
+ "grad_norm": 15.48339557647705,
723
+ "learning_rate": 0.0,
724
+ "loss": 5.1382,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.018789928598271326,
729
+ "eval_loss": 1.2692981958389282,
730
+ "eval_runtime": 828.1962,
731
+ "eval_samples_per_second": 10.824,
732
+ "eval_steps_per_second": 5.412,
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": 1.6778451655380173e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null