prxy5606 commited on
Commit
edce97c
·
verified ·
1 Parent(s): de5699f

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 sha256:45a210e18f963e9364551fa2d459b87dd03e5eac7e046b3b0a235acfa7125416
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ffa2061f86ef65086dbc235364a3c77205cc5c9bbe3e549b10efc8a660cc80
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e8becf4a15cbc3a9497ac10dde0131e5776cfd4e9c635106f4b8972c6166e6c
3
  size 591203178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:022cb2be1e1178cd90c20fe1a5ebcc954a5a2099479d35e39e1796566f355317
3
  size 591203178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ec23ceedda3600099b07b897f20df8cec807c62901f82ff73b0355ccf02a336
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb1df1de9a1ef560f024ee749e11f0224911ef63f7e8197f011275b9864b8b4
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": 2.8629980087280273,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.00816293212521938,
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": 28.374,
374
  "eval_steps_per_second": 14.187,
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": 1.367527271694336e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.735139846801758,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.01632586425043876,
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": 28.374,
374
  "eval_steps_per_second": 14.187,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008326190767723767,
379
+ "grad_norm": 2.1676950454711914,
380
+ "learning_rate": 7.938926261462366e-05,
381
+ "loss": 2.8331,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008489449410228153,
386
+ "grad_norm": 1.6274971961975098,
387
+ "learning_rate": 7.754484907260513e-05,
388
+ "loss": 2.6935,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.00865270805273254,
393
+ "grad_norm": 1.3204303979873657,
394
+ "learning_rate": 7.564496387029532e-05,
395
+ "loss": 2.797,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.008815966695236929,
400
+ "grad_norm": 1.0049480199813843,
401
+ "learning_rate": 7.369343312364993e-05,
402
+ "loss": 3.0168,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008979225337741316,
407
+ "grad_norm": 1.075304388999939,
408
+ "learning_rate": 7.169418695587791e-05,
409
+ "loss": 3.2103,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.009142483980245704,
414
+ "grad_norm": 0.8386501669883728,
415
+ "learning_rate": 6.965125158269619e-05,
416
+ "loss": 3.072,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009305742622750092,
421
+ "grad_norm": 0.8426527976989746,
422
+ "learning_rate": 6.756874120406714e-05,
423
+ "loss": 2.752,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00946900126525448,
428
+ "grad_norm": 0.8528467416763306,
429
+ "learning_rate": 6.545084971874738e-05,
430
+ "loss": 2.8089,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009632259907758867,
435
+ "grad_norm": 0.904664158821106,
436
+ "learning_rate": 6.330184227833376e-05,
437
+ "loss": 2.8771,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009795518550263255,
442
+ "grad_norm": 0.7004697322845459,
443
+ "learning_rate": 6.112604669781572e-05,
444
+ "loss": 2.6807,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.009958777192767642,
449
+ "grad_norm": 0.7690675258636475,
450
+ "learning_rate": 5.8927844739931834e-05,
451
+ "loss": 2.9141,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.01012203583527203,
456
+ "grad_norm": 0.7248542904853821,
457
+ "learning_rate": 5.6711663290882776e-05,
458
+ "loss": 2.8913,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010285294477776418,
463
+ "grad_norm": 0.617339015007019,
464
+ "learning_rate": 5.448196544517168e-05,
465
+ "loss": 2.8585,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010448553120280805,
470
+ "grad_norm": 0.7304785251617432,
471
+ "learning_rate": 5.2243241517525754e-05,
472
+ "loss": 2.6997,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010611811762785193,
477
+ "grad_norm": 0.8117228150367737,
478
+ "learning_rate": 5e-05,
479
+ "loss": 2.8935,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.01077507040528958,
484
+ "grad_norm": 0.7086424827575684,
485
+ "learning_rate": 4.775675848247427e-05,
486
+ "loss": 2.969,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.010938329047793967,
491
+ "grad_norm": 0.715423583984375,
492
+ "learning_rate": 4.551803455482833e-05,
493
+ "loss": 2.5869,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.011101587690298355,
498
+ "grad_norm": 0.7727792263031006,
499
+ "learning_rate": 4.328833670911724e-05,
500
+ "loss": 2.8389,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011264846332802742,
505
+ "grad_norm": 0.6761236786842346,
506
+ "learning_rate": 4.107215526006817e-05,
507
+ "loss": 2.709,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01142810497530713,
512
+ "grad_norm": 0.7613105773925781,
513
+ "learning_rate": 3.887395330218429e-05,
514
+ "loss": 2.8757,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011591363617811518,
519
+ "grad_norm": 0.8669199347496033,
520
+ "learning_rate": 3.6698157721666246e-05,
521
+ "loss": 3.1531,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011754622260315905,
526
+ "grad_norm": 0.8836479783058167,
527
+ "learning_rate": 3.4549150281252636e-05,
528
+ "loss": 2.7458,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.011917880902820293,
533
+ "grad_norm": 0.778107225894928,
534
+ "learning_rate": 3.243125879593286e-05,
535
+ "loss": 2.7683,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.01208113954532468,
540
+ "grad_norm": 0.6686323285102844,
541
+ "learning_rate": 3.0348748417303823e-05,
542
+ "loss": 2.4992,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012244398187829068,
547
+ "grad_norm": 0.8155844807624817,
548
+ "learning_rate": 2.8305813044122097e-05,
549
+ "loss": 2.8288,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012407656830333456,
554
+ "grad_norm": 0.7905011773109436,
555
+ "learning_rate": 2.630656687635007e-05,
556
+ "loss": 2.7207,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.012570915472837844,
561
+ "grad_norm": 0.821061372756958,
562
+ "learning_rate": 2.43550361297047e-05,
563
+ "loss": 2.6178,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012734174115342231,
568
+ "grad_norm": 0.9048423767089844,
569
+ "learning_rate": 2.245515092739488e-05,
570
+ "loss": 2.8052,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.01289743275784662,
575
+ "grad_norm": 0.7810814380645752,
576
+ "learning_rate": 2.061073738537635e-05,
577
+ "loss": 2.9147,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.013060691400351007,
582
+ "grad_norm": 0.887985348701477,
583
+ "learning_rate": 1.8825509907063327e-05,
584
+ "loss": 2.681,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.013223950042855395,
589
+ "grad_norm": 0.8398605585098267,
590
+ "learning_rate": 1.7103063703014372e-05,
591
+ "loss": 2.7676,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.01338720868535978,
596
+ "grad_norm": 0.8217864036560059,
597
+ "learning_rate": 1.544686755065677e-05,
598
+ "loss": 2.7269,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.013550467327864168,
603
+ "grad_norm": 0.9799962639808655,
604
+ "learning_rate": 1.3860256808630428e-05,
605
+ "loss": 2.7334,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013713725970368556,
610
+ "grad_norm": 0.7503747344017029,
611
+ "learning_rate": 1.2346426699819458e-05,
612
+ "loss": 2.6707,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.013876984612872944,
617
+ "grad_norm": 0.9742613434791565,
618
+ "learning_rate": 1.090842587659851e-05,
619
+ "loss": 2.6392,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.014040243255377331,
624
+ "grad_norm": 0.7584743499755859,
625
+ "learning_rate": 9.549150281252633e-06,
626
+ "loss": 2.6515,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.014203501897881719,
631
+ "grad_norm": 0.7804672718048096,
632
+ "learning_rate": 8.271337313934869e-06,
633
+ "loss": 2.4738,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.014366760540386107,
638
+ "grad_norm": 0.8059239983558655,
639
+ "learning_rate": 7.077560319906695e-06,
640
+ "loss": 2.494,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.014530019182890494,
645
+ "grad_norm": 0.9126543402671814,
646
+ "learning_rate": 5.9702234071631e-06,
647
+ "loss": 2.6029,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.014693277825394882,
652
+ "grad_norm": 0.8912916779518127,
653
+ "learning_rate": 4.951556604879048e-06,
654
+ "loss": 2.5753,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.01485653646789927,
659
+ "grad_norm": 0.9568765163421631,
660
+ "learning_rate": 4.023611372427471e-06,
661
+ "loss": 2.3926,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.015019795110403657,
666
+ "grad_norm": 1.004371166229248,
667
+ "learning_rate": 3.18825646801314e-06,
668
+ "loss": 2.7712,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.015183053752908045,
673
+ "grad_norm": 1.0826361179351807,
674
+ "learning_rate": 2.4471741852423237e-06,
675
+ "loss": 2.6105,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015346312395412433,
680
+ "grad_norm": 0.9342916011810303,
681
+ "learning_rate": 1.8018569652073381e-06,
682
+ "loss": 2.3885,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.01550957103791682,
687
+ "grad_norm": 1.158676028251648,
688
+ "learning_rate": 1.2536043909088191e-06,
689
+ "loss": 2.4456,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.015672829680421208,
694
+ "grad_norm": 1.0513296127319336,
695
+ "learning_rate": 8.035205700685167e-07,
696
+ "loss": 2.2801,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.015836088322925594,
701
+ "grad_norm": 1.4424023628234863,
702
+ "learning_rate": 4.52511911603265e-07,
703
+ "loss": 2.6424,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.015999346965429984,
708
+ "grad_norm": 1.7463353872299194,
709
+ "learning_rate": 2.012853002380466e-07,
710
+ "loss": 2.3797,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.01616260560793437,
715
+ "grad_norm": 2.0830276012420654,
716
+ "learning_rate": 5.0346672934270534e-08,
717
+ "loss": 2.5996,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.01632586425043876,
722
+ "grad_norm": 2.8903799057006836,
723
+ "learning_rate": 0.0,
724
+ "loss": 2.8615,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.01632586425043876,
729
+ "eval_loss": 2.735139846801758,
730
+ "eval_runtime": 363.8754,
731
+ "eval_samples_per_second": 28.35,
732
+ "eval_steps_per_second": 14.175,
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": 2.728250925121536e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null