aleegis09 commited on
Commit
16ce6d5
·
verified ·
1 Parent(s): 3369dfe

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:cc94408cdf3090776f16e7d92e56afb5d81450a395d83bfe4b0691d7c6d34de2
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18cdf4c1e94caeb7246d98bd902ebd7e7186239b676074e9aafff309bfc7ef53
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0f4d7c693b8bbd2fbf45616daa5b407aca0138653f1b60a1a9cbf06738869b2
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652168d2c59dab8dc5357bf4f543d9889e5705ceb72a35fbb1a051cea8c76d9d
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a1b580ba639beebafd8fffa0dc7cb727f86689732f14f59b9d2e8a590d3e9b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e31e37afd19c26fe63a4fe0cf95fe7e01d072d7e4539409bdd070401a42711
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": 1.6620087623596191,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.07122507122507123,
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": 22.349,
374
  "eval_steps_per_second": 5.597,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.0821993309863936e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5862289667129517,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.14245014245014245,
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": 22.349,
374
  "eval_steps_per_second": 5.597,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07264957264957266,
379
+ "grad_norm": 1.8428657054901123,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.2133,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07407407407407407,
386
+ "grad_norm": 2.1231138706207275,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.4196,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0754985754985755,
393
+ "grad_norm": 1.6163792610168457,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.3055,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.07692307692307693,
400
+ "grad_norm": 1.194074034690857,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.1933,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.07834757834757834,
407
+ "grad_norm": 1.0080146789550781,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.2088,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.07977207977207977,
414
+ "grad_norm": 0.73309326171875,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.1147,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.0811965811965812,
421
+ "grad_norm": 0.6256619095802307,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.0787,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.08262108262108261,
428
+ "grad_norm": 0.6739497184753418,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.1465,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08404558404558404,
435
+ "grad_norm": 0.7923569083213806,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.182,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.08547008547008547,
442
+ "grad_norm": 0.8488563299179077,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.2106,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0868945868945869,
449
+ "grad_norm": 0.8478406071662903,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.1505,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.08831908831908832,
456
+ "grad_norm": 0.8413639068603516,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.1692,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.08974358974358974,
463
+ "grad_norm": 0.7861711382865906,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.1316,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.09116809116809117,
470
+ "grad_norm": 0.7624171376228333,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.1516,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.09259259259259259,
477
+ "grad_norm": 0.7577725648880005,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.115,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09401709401709402,
484
+ "grad_norm": 0.7820805311203003,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.0262,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.09544159544159544,
491
+ "grad_norm": 0.8114756345748901,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0623,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.09686609686609686,
498
+ "grad_norm": 0.8904410004615784,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.0902,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.09829059829059829,
505
+ "grad_norm": 0.9297963976860046,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.1,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.09971509971509972,
512
+ "grad_norm": 1.0232235193252563,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.0924,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.10113960113960115,
519
+ "grad_norm": 1.0157926082611084,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.0979,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.10256410256410256,
526
+ "grad_norm": 1.0584907531738281,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.0371,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.10398860398860399,
533
+ "grad_norm": 1.143020749092102,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.026,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.10541310541310542,
540
+ "grad_norm": 1.184112548828125,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.9999,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.10683760683760683,
547
+ "grad_norm": 1.411512851715088,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.1171,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.10826210826210826,
554
+ "grad_norm": 1.5346912145614624,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.0003,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.10968660968660969,
561
+ "grad_norm": 2.24712872505188,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.2975,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.1111111111111111,
568
+ "grad_norm": 2.241441011428833,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.0772,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.11253561253561253,
575
+ "grad_norm": 3.3355181217193604,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.3215,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.11396011396011396,
582
+ "grad_norm": 2.3127119541168213,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.0156,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.11538461538461539,
589
+ "grad_norm": 2.2935128211975098,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.9638,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1168091168091168,
596
+ "grad_norm": 2.777211904525757,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.1279,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.11823361823361823,
603
+ "grad_norm": 2.671398639678955,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2885,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.11965811965811966,
610
+ "grad_norm": 3.616776943206787,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.5908,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.12108262108262108,
617
+ "grad_norm": 2.932478427886963,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.3571,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1225071225071225,
624
+ "grad_norm": 2.3018410205841064,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.0595,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.12393162393162394,
631
+ "grad_norm": 2.408008337020874,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.5027,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.12535612535612536,
638
+ "grad_norm": 2.7625410556793213,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.7931,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.1267806267806268,
645
+ "grad_norm": 3.301805257797241,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.9967,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.1282051282051282,
652
+ "grad_norm": 3.297290563583374,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.0517,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.12962962962962962,
659
+ "grad_norm": 3.5428030490875244,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.2671,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.13105413105413105,
666
+ "grad_norm": 3.5359692573547363,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.1285,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.13247863247863248,
673
+ "grad_norm": 3.873988151550293,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.1496,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.1339031339031339,
680
+ "grad_norm": 4.848047733306885,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.4119,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.13532763532763534,
687
+ "grad_norm": 5.2075300216674805,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.6581,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.13675213675213677,
694
+ "grad_norm": 4.486565113067627,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.3495,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.13817663817663817,
701
+ "grad_norm": 4.8237175941467285,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.9713,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.1396011396011396,
708
+ "grad_norm": 5.597812175750732,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.4004,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.14102564102564102,
715
+ "grad_norm": 5.861245632171631,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.9003,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.14245014245014245,
722
+ "grad_norm": 7.58296012878418,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.8815,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.14245014245014245,
729
+ "eval_loss": 1.5862289667129517,
730
+ "eval_runtime": 52.8852,
731
+ "eval_samples_per_second": 22.35,
732
+ "eval_steps_per_second": 5.597,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.154039461321114e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null