prxy5608 commited on
Commit
d661b04
·
verified ·
1 Parent(s): 23afd0c

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:fee542b148308d87c92c6f701a882d4afeb7ebe27ee4ae950d73f409cf2f097b
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df05f346f178ea3e87faca0f961c166bc06cac5670fdcfcd19796807e9cd9f5f
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54a0bd265fafee9f1ee709558d57fd6411d749737e6d37cb73f88a9b51a04637
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a1c9e495202516c5ea4b4804c516f84c54025f817e845c9c653858a878ecf01
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:326134f5554cff3eae637687ed7e80072d43491d82c7f7bcb0c892b6da812b73
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f35b777cff15c37dfb5a07dbd2b17199632739a7fe0db66cf294d11cd19cfd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d359eb5d29e75fb2bbe5b7026981da69b95b8ad1fea469302d13cde104f7e8a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.9773313403129578,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.28653295128939826,
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": 9.184,
374
  "eval_steps_per_second": 2.312,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.1125287643250688e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.4951989948749542,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.5730659025787965,
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": 9.184,
374
  "eval_steps_per_second": 2.312,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.2922636103151863,
379
+ "grad_norm": 1.1332144737243652,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.7462,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.2979942693409742,
386
+ "grad_norm": 1.1906083822250366,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.718,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3037249283667622,
393
+ "grad_norm": 5.363713264465332,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.9616,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.30945558739255014,
400
+ "grad_norm": 15.01010799407959,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.598,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.3151862464183381,
407
+ "grad_norm": 4.782071113586426,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.6581,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.3209169054441261,
414
+ "grad_norm": 12.04438304901123,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.6126,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.32664756446991405,
421
+ "grad_norm": 7.532559394836426,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.3906,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.332378223495702,
428
+ "grad_norm": 2.730405330657959,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.3392,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.33810888252148996,
435
+ "grad_norm": 2.608391523361206,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.3518,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3438395415472779,
442
+ "grad_norm": 17.62820816040039,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.6,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.3495702005730659,
449
+ "grad_norm": 3.376549482345581,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.8442,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.3553008595988539,
456
+ "grad_norm": 2.771148920059204,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.7439,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.36103151862464183,
463
+ "grad_norm": 1.198996901512146,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.4989,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.3667621776504298,
470
+ "grad_norm": 1.346926212310791,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.6355,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.37249283667621774,
477
+ "grad_norm": 1.0279195308685303,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.5252,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.37822349570200575,
484
+ "grad_norm": 1.1113489866256714,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.4989,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3839541547277937,
491
+ "grad_norm": 1.2599353790283203,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.6129,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.38968481375358166,
498
+ "grad_norm": 1.3951442241668701,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.6764,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.3954154727793696,
505
+ "grad_norm": 0.8668970465660095,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.6259,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.40114613180515757,
512
+ "grad_norm": 0.9053806066513062,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.5455,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.4068767908309456,
519
+ "grad_norm": 1.2135175466537476,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.7378,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.41260744985673353,
526
+ "grad_norm": 0.8739562630653381,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.567,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.4183381088825215,
533
+ "grad_norm": 0.8985298871994019,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.5861,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.42406876790830944,
540
+ "grad_norm": 0.808602511882782,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.4248,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.4297994269340974,
547
+ "grad_norm": 0.9335209727287292,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.5191,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.4355300859598854,
554
+ "grad_norm": 0.7914756536483765,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.4788,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.44126074498567336,
561
+ "grad_norm": 1.1445316076278687,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.5361,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.4469914040114613,
568
+ "grad_norm": 0.8748629093170166,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.499,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.45272206303724927,
575
+ "grad_norm": 1.1068371534347534,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.5626,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.4584527220630373,
582
+ "grad_norm": 1.013913869857788,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.5701,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.46418338108882523,
589
+ "grad_norm": 0.8930913209915161,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.4473,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.4699140401146132,
596
+ "grad_norm": 0.8025099039077759,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.4006,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.47564469914040114,
603
+ "grad_norm": 1.2134878635406494,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.5306,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.4813753581661891,
610
+ "grad_norm": 1.2197167873382568,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.6729,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.4871060171919771,
617
+ "grad_norm": 1.0436406135559082,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.5937,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.49283667621776506,
624
+ "grad_norm": 1.3491209745407104,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.5954,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.498567335243553,
631
+ "grad_norm": 0.75426185131073,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.7653,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.504297994269341,
638
+ "grad_norm": 0.7373204231262207,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.8416,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.5100286532951289,
645
+ "grad_norm": 0.683611273765564,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.7598,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.5157593123209169,
652
+ "grad_norm": 0.7615026831626892,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.8549,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.5214899713467048,
659
+ "grad_norm": 0.7129623293876648,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.6896,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.5272206303724928,
666
+ "grad_norm": 0.7031312584877014,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.7698,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.5329512893982808,
673
+ "grad_norm": 0.8572548031806946,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.5967,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.5386819484240688,
680
+ "grad_norm": 1.1666706800460815,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.5839,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.5444126074498568,
687
+ "grad_norm": 1.0940685272216797,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.5916,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.5501432664756447,
694
+ "grad_norm": 1.2334367036819458,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.4533,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.5558739255014327,
701
+ "grad_norm": 5.839780807495117,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.4335,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.5616045845272206,
708
+ "grad_norm": 1.2165459394454956,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.3048,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.5673352435530086,
715
+ "grad_norm": 4.578935623168945,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.3554,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.5730659025787965,
722
+ "grad_norm": 4.122792720794678,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.4068,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.5730659025787965,
729
+ "eval_loss": 0.4951989948749542,
730
+ "eval_runtime": 31.4583,
731
+ "eval_samples_per_second": 9.346,
732
+ "eval_steps_per_second": 2.352,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.232600096543867e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null