nttx commited on
Commit
aadf04f
·
verified ·
1 Parent(s): 03736ab

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 sha256:47d0f70225c53f9658a975ca4926b69e9d7c8dbeb051fbc5c5ae5c44e2dc141c
3
  size 289452128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527c620c8f76060997d8d29add6d54e8a4bbb01302f4e972970f642d422e0ffe
3
  size 289452128
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce0710113b9803b3bbaa9cb3dc082acfb3e42e0cb56495d75616cf4123c14ef2
3
  size 147359892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2720e34bc517dd05a8866fc0c4ef6b9ca36077ba43f1ade1844d7dfd2415f058
3
  size 147359892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04eeb213be82c8d7e78418cd6a261124ae37b3e0527f4017e3d5378d4bf92842
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8b8836f43a546956a1bc8471fcdba26d9404b35197da2230ed9e0902488491
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": 0.9435171484947205,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.07510326699211416,
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": 33.701,
374
  "eval_steps_per_second": 8.44,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.6627926527115264e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5659072399139404,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.1502065339842283,
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": 33.701,
374
  "eval_steps_per_second": 8.44,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07660533233195645,
379
+ "grad_norm": 5.346027851104736,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.3858,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07810739767179872,
386
+ "grad_norm": 4.529382228851318,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.1019,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.07960946301164101,
393
+ "grad_norm": 2.0946102142333984,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.7455,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.08111152835148329,
400
+ "grad_norm": 0.4784291386604309,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.6575,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.08261359369132558,
407
+ "grad_norm": 0.43049320578575134,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.6418,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.08411565903116786,
414
+ "grad_norm": 0.3956131637096405,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.6338,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.08561772437101015,
421
+ "grad_norm": 0.3648943603038788,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.6281,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.08711978971085242,
428
+ "grad_norm": 0.265221506357193,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.6154,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08862185505069471,
435
+ "grad_norm": 0.3286784887313843,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.6275,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.09012392039053699,
442
+ "grad_norm": 0.36223769187927246,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.6223,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.09162598573037928,
449
+ "grad_norm": 0.2875317931175232,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.614,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.09312805107022155,
456
+ "grad_norm": 0.24351203441619873,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.5952,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.09463011641006384,
463
+ "grad_norm": 0.2812121510505676,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.6036,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.09613218174990612,
470
+ "grad_norm": 0.2832166850566864,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.5976,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.09763424708974841,
477
+ "grad_norm": 0.2672559916973114,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.5743,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09913631242959069,
484
+ "grad_norm": 0.25090304017066956,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.5795,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.10063837776943298,
491
+ "grad_norm": 0.3040817677974701,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.5613,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.10214044310927525,
498
+ "grad_norm": 0.23814338445663452,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.5521,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.10364250844911754,
505
+ "grad_norm": 0.2542641758918762,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.5535,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.10514457378895982,
512
+ "grad_norm": 0.2717762887477875,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.5361,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.10664663912880211,
519
+ "grad_norm": 0.2743045389652252,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.5338,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.10814870446864439,
526
+ "grad_norm": 0.22834768891334534,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.5238,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.10965076980848668,
533
+ "grad_norm": 0.3098483085632324,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.5278,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.11115283514832895,
540
+ "grad_norm": 0.2830328941345215,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.5089,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.11265490048817124,
547
+ "grad_norm": 0.2570495009422302,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.4981,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.11415696582801352,
554
+ "grad_norm": 0.27931836247444153,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.4863,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.11565903116785581,
561
+ "grad_norm": 0.2561793625354767,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.4959,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.11716109650769808,
568
+ "grad_norm": 0.29976847767829895,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.4882,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.11866316184754037,
575
+ "grad_norm": 0.27593934535980225,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.4959,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.12016522718738265,
582
+ "grad_norm": 0.2488517165184021,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.4699,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.12166729252722494,
589
+ "grad_norm": 0.19852301478385925,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.4576,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.12316935786706722,
596
+ "grad_norm": 0.2308630794286728,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.4519,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.1246714232069095,
603
+ "grad_norm": 0.28317439556121826,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.4773,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.12617348854675178,
610
+ "grad_norm": 0.280638188123703,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.4727,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.12767555388659407,
617
+ "grad_norm": 0.29901838302612305,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.463,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.12917761922643636,
624
+ "grad_norm": 0.32130149006843567,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.4546,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.13067968456627863,
631
+ "grad_norm": 0.24742907285690308,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.4519,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.13218174990612092,
638
+ "grad_norm": 0.2867355942726135,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.4445,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.1336838152459632,
645
+ "grad_norm": 0.27279844880104065,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.4328,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.1351858805858055,
652
+ "grad_norm": 0.25699475407600403,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.4397,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.13668794592564776,
659
+ "grad_norm": 0.2791455090045929,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.4523,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.13819001126549005,
666
+ "grad_norm": 0.3582814335823059,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.4553,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.13969207660533234,
673
+ "grad_norm": 0.28347545862197876,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.4314,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.14119414194517463,
680
+ "grad_norm": 0.2645236551761627,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.4493,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.1426962072850169,
687
+ "grad_norm": 0.308789998292923,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.4487,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.14419827262485918,
694
+ "grad_norm": 0.27754440903663635,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.4236,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.14570033796470147,
701
+ "grad_norm": 0.29128730297088623,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.4523,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.14720240330454376,
708
+ "grad_norm": 0.4283706247806549,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.4624,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.14870446864438602,
715
+ "grad_norm": 0.3860466480255127,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.4384,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.1502065339842283,
722
+ "grad_norm": 0.4692773222923279,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.4551,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.1502065339842283,
729
+ "eval_loss": 0.5659072399139404,
730
+ "eval_runtime": 33.2992,
731
+ "eval_samples_per_second": 33.694,
732
+ "eval_steps_per_second": 8.439,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 3.3173127051608064e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null