abaddon182 commited on
Commit
bf931a3
·
verified ·
1 Parent(s): 99d4eab

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 sha256:331ccd56c372a6ff89755a68dd9b5edb188815d343d65ca2690a75217363f4a8
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a6a5eb5d0f01b55bf5b3818d537e74003b77a052ad1c016feb1847244dafc0
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e54c010b95e2fd0839aae72c7cc74f3dbfa7a5c853b077cb18b288853262e008
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb91355981dec61999852dc8f57fcfc97b59f0a4dd88b94f535b66304fb3dcb
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10841dd1f83a11fb56098f7d9238292cfa9091d460a622f53c2c7d6d43d6400a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4aa299887e9b2f4f91c78948953289b823e5f532cea1915d4cd0ba02b14f07
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": 1.7481515407562256,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.00801667468334135,
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": 58.018,
374
  "eval_steps_per_second": 14.509,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3864241215897600.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.577565312385559,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0160333493666827,
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": 58.018,
374
  "eval_steps_per_second": 14.509,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008177008177008177,
379
+ "grad_norm": 4.216922760009766,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.9413,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008337341670675003,
386
+ "grad_norm": 4.562152862548828,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.3296,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.008497675164341831,
393
+ "grad_norm": 3.430103302001953,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.4943,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.008658008658008658,
400
+ "grad_norm": 3.834789276123047,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.6902,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008818342151675485,
407
+ "grad_norm": 2.8888132572174072,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.8122,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.008978675645342313,
414
+ "grad_norm": 1.801705002784729,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.9578,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.00913900913900914,
421
+ "grad_norm": 2.326319932937622,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.9303,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.009299342632675966,
428
+ "grad_norm": 2.414191722869873,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.0898,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009459676126342792,
435
+ "grad_norm": 2.116661787033081,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.2721,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.00962000962000962,
442
+ "grad_norm": 1.7814158201217651,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.7448,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.009780343113676447,
449
+ "grad_norm": 1.5620167255401611,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.8467,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.009940676607343274,
456
+ "grad_norm": 1.5871108770370483,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.0595,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010101010101010102,
463
+ "grad_norm": 1.481527328491211,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.6665,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010261343594676928,
470
+ "grad_norm": 1.3492636680603027,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.7218,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010421677088343755,
477
+ "grad_norm": 1.5018565654754639,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.9853,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.010582010582010581,
484
+ "grad_norm": 1.436688780784607,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.061,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.01074234407567741,
491
+ "grad_norm": 1.468376874923706,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.6864,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.010902677569344236,
498
+ "grad_norm": 1.5045324563980103,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.899,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011063011063011063,
505
+ "grad_norm": 1.4142143726348877,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.0851,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.01122334455667789,
512
+ "grad_norm": 1.4256950616836548,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.9298,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011383678050344717,
519
+ "grad_norm": 1.4729069471359253,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.6926,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011544011544011544,
526
+ "grad_norm": 1.4505417346954346,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.6073,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.01170434503767837,
533
+ "grad_norm": 1.528064489364624,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.7171,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.011864678531345199,
540
+ "grad_norm": 1.5659871101379395,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.9315,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012025012025012025,
547
+ "grad_norm": 1.6519936323165894,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.9801,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012185345518678852,
554
+ "grad_norm": 1.474597454071045,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.5052,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.012345679012345678,
561
+ "grad_norm": 1.4802509546279907,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.4324,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012506012506012507,
568
+ "grad_norm": 1.6556718349456787,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.6473,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.012666345999679333,
575
+ "grad_norm": 1.578564167022705,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.6985,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.01282667949334616,
582
+ "grad_norm": 1.5099948644638062,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.5524,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.012987012987012988,
589
+ "grad_norm": 1.6673612594604492,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.5226,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.013147346480679814,
596
+ "grad_norm": 1.7997468709945679,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.5043,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.013307679974346641,
603
+ "grad_norm": 1.7401671409606934,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.1924,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013468013468013467,
610
+ "grad_norm": 1.8019427061080933,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.1919,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.013628346961680296,
617
+ "grad_norm": 1.8377891778945923,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.1958,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.013788680455347122,
624
+ "grad_norm": 1.9431484937667847,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.2923,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.013949013949013949,
631
+ "grad_norm": 1.7748252153396606,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.0951,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.014109347442680775,
638
+ "grad_norm": 1.8332815170288086,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.1729,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.014269680936347603,
645
+ "grad_norm": 2.066511869430542,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.2436,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.01443001443001443,
652
+ "grad_norm": 1.8436999320983887,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.2209,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.014590347923681257,
659
+ "grad_norm": 1.9777435064315796,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.1729,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.014750681417348085,
666
+ "grad_norm": 1.988520622253418,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.2026,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.014911014911014911,
673
+ "grad_norm": 2.101755380630493,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.229,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015071348404681738,
680
+ "grad_norm": 2.1809160709381104,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.0617,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.015231681898348564,
687
+ "grad_norm": 2.251002073287964,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.326,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.015392015392015393,
694
+ "grad_norm": 2.272563934326172,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.0713,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.015552348885682219,
701
+ "grad_norm": 3.0095102787017822,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.1834,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.015712682379349047,
708
+ "grad_norm": 2.3724913597106934,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.0536,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.015873015873015872,
715
+ "grad_norm": 3.3596227169036865,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.9999,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0160333493666827,
722
+ "grad_norm": 4.8523383140563965,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.9932,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0160333493666827,
729
+ "eval_loss": 1.577565312385559,
730
+ "eval_runtime": 181.1273,
731
+ "eval_samples_per_second": 57.998,
732
+ "eval_steps_per_second": 14.504,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 7728482431795200.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null