aleegis09 commited on
Commit
2bcce37
·
verified ·
1 Parent(s): 72832bf

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 sha256:4a157ef3436daa2171362af223966c63eda0ee6d86ef19a8d581ce0f3299d86d
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4079b1eb838e707578f33fbb517c438d4486f8ceb9df8eb4e051edccfa1ff5f2
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bf7ecb483f38b6b9b1c64dd6c3c79b8077daa1630902fc81c3c17e621265476
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427b49f84cf5588b11dbd5676261a9ea1dfe2d0511490fc33949a4c109766475
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:607b6e24600a9ad7f9026eea983bad3ed854b4f4169b23974bb8e9b21df319c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c70073add896fa025a69a52fd9e82f9ade4de4cab656012b0622c0953b45d9
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": 0.6425667405128479,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.13689253935660506,
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": 12.733,
374
  "eval_steps_per_second": 3.188,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.65570641213522e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6070587635040283,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.2737850787132101,
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": 12.733,
374
  "eval_steps_per_second": 3.188,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.13963039014373715,
379
+ "grad_norm": 0.844247043132782,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.4031,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.14236824093086928,
386
+ "grad_norm": 0.5820806622505188,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.4638,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.14510609171800137,
393
+ "grad_norm": 0.566764771938324,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.4813,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.14784394250513347,
400
+ "grad_norm": 0.4588389992713928,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.3922,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.15058179329226556,
407
+ "grad_norm": 0.3991678059101105,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.5259,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.15331964407939766,
414
+ "grad_norm": 0.46561309695243835,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.4653,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.15605749486652978,
421
+ "grad_norm": 0.5909699201583862,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.4833,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.15879534565366188,
428
+ "grad_norm": 0.5626156330108643,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.4268,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.16153319644079397,
435
+ "grad_norm": 0.5996052622795105,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.4868,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.16427104722792607,
442
+ "grad_norm": 0.5262600779533386,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.4627,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.16700889801505817,
449
+ "grad_norm": 0.6106951236724854,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.6943,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.1697467488021903,
456
+ "grad_norm": 0.7453521490097046,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.5761,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.17248459958932238,
463
+ "grad_norm": 0.5354063510894775,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.5746,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.17522245037645448,
470
+ "grad_norm": 0.46529680490493774,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.4092,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.17796030116358658,
477
+ "grad_norm": 0.5710752606391907,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.5175,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.1806981519507187,
484
+ "grad_norm": 0.5328500270843506,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.6461,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.1834360027378508,
491
+ "grad_norm": 0.571149468421936,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.5596,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.1861738535249829,
498
+ "grad_norm": 0.5339324474334717,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.5303,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.188911704312115,
505
+ "grad_norm": 0.6434739232063293,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.5518,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.19164955509924708,
512
+ "grad_norm": 0.5670827031135559,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.618,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.1943874058863792,
519
+ "grad_norm": 0.512898862361908,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.524,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.1971252566735113,
526
+ "grad_norm": 0.6344662308692932,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.5645,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.1998631074606434,
533
+ "grad_norm": 0.4935149848461151,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.6053,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.2026009582477755,
540
+ "grad_norm": 0.5701279044151306,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.6284,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.2053388090349076,
547
+ "grad_norm": 0.5761316418647766,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.499,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2080766598220397,
554
+ "grad_norm": 0.5786774754524231,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.5389,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.2108145106091718,
561
+ "grad_norm": 0.6124125123023987,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.7289,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.2135523613963039,
568
+ "grad_norm": 0.5064036250114441,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.599,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.216290212183436,
575
+ "grad_norm": 0.5362352728843689,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.6196,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.2190280629705681,
582
+ "grad_norm": 0.6147336363792419,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.6641,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.22176591375770022,
589
+ "grad_norm": 0.597585141658783,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.6222,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.2245037645448323,
596
+ "grad_norm": 0.6162816286087036,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.6771,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.2272416153319644,
603
+ "grad_norm": 0.5572537779808044,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.6536,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.2299794661190965,
610
+ "grad_norm": 0.5686996579170227,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.6136,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2327173169062286,
617
+ "grad_norm": 0.5509069561958313,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.5289,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.23545516769336072,
624
+ "grad_norm": 0.6756793856620789,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.7809,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.23819301848049282,
631
+ "grad_norm": 0.6623716950416565,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.7026,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.24093086926762491,
638
+ "grad_norm": 0.6078564524650574,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.6284,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.243668720054757,
645
+ "grad_norm": 0.5939504504203796,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.6526,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.2464065708418891,
652
+ "grad_norm": 0.7013550400733948,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.6582,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.24914442162902123,
659
+ "grad_norm": 0.5962901711463928,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.6444,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.2518822724161533,
666
+ "grad_norm": 0.7413282990455627,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.6981,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.2546201232032854,
673
+ "grad_norm": 0.7161607146263123,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.6812,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.25735797399041754,
680
+ "grad_norm": 0.7952245473861694,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.7068,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.2600958247775496,
687
+ "grad_norm": 0.6638028025627136,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.6078,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.26283367556468173,
694
+ "grad_norm": 0.802947461605072,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.7225,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.2655715263518138,
701
+ "grad_norm": 0.7005895376205444,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.6568,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.2683093771389459,
708
+ "grad_norm": 0.7152554392814636,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.5274,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.27104722792607805,
715
+ "grad_norm": 0.9021908640861511,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.6019,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.2737850787132101,
722
+ "grad_norm": 0.9411377310752869,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.5534,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.2737850787132101,
729
+ "eval_loss": 0.6070587635040283,
730
+ "eval_runtime": 48.3414,
731
+ "eval_samples_per_second": 12.722,
732
+ "eval_steps_per_second": 3.186,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.531141282427044e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null