prxy5606 commited on
Commit
2794516
·
verified ·
1 Parent(s): 5a843f6

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:c8ffb13b5e4a0972a7f9220677a509ead328c5c83189b4cf35bed87729ae78a8
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5116d3bec13e687d8ef4597838ecbc7db8d547c7329eb0cc759c6ccbde00cbdf
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5eb80053779fd205e30ca637c8830ba55feba88f7d5b2215486d0533f608b3d
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef0e2753ffcd187783dca0f4dcd0ed6865afce071788d0b921f1d0053616769e
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:b4e4209f68d3266a698829c1979f8880db6c9cc9ef2496983917703b0cd99e79
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d68b0d1e95502cbd9a90afd80df31b3c61f572313298df32576640984b53316
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": 0.005154376849532127,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.003683241252302026,
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": 12.682,
374
  "eval_steps_per_second": 3.17,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.844270609478451e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.0033941082656383514,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.007366482504604052,
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": 12.682,
374
  "eval_steps_per_second": 3.17,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.0037569060773480663,
379
+ "grad_norm": 0.14203476905822754,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.0496,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.0038305709023941066,
386
+ "grad_norm": 0.14956742525100708,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.0236,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0039042357274401474,
393
+ "grad_norm": 0.06372524052858353,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.0177,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.003977900552486188,
400
+ "grad_norm": 0.05046476051211357,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.0012,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.004051565377532229,
407
+ "grad_norm": 0.062402307987213135,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.004,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.004125230202578269,
414
+ "grad_norm": 0.014747344888746738,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.0004,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.004198895027624309,
421
+ "grad_norm": 0.07069471478462219,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.0021,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00427255985267035,
428
+ "grad_norm": 0.05206258222460747,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0016,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.00434622467771639,
435
+ "grad_norm": 0.1130603477358818,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.0074,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.004419889502762431,
442
+ "grad_norm": 0.011621471494436264,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.0003,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.004493554327808472,
449
+ "grad_norm": 0.08598984777927399,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.0024,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.004567219152854512,
456
+ "grad_norm": 0.014879305846989155,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0005,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.004640883977900552,
463
+ "grad_norm": 0.014751851558685303,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.0005,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.004714548802946593,
470
+ "grad_norm": 0.053578369319438934,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.0012,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.004788213627992633,
477
+ "grad_norm": 0.02008475735783577,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0004,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.004861878453038674,
484
+ "grad_norm": 0.057756297290325165,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.0006,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.004935543278084715,
491
+ "grad_norm": 0.02606124058365822,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0004,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.005009208103130755,
498
+ "grad_norm": 0.014606554992496967,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0003,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.005082872928176795,
505
+ "grad_norm": 0.03155618533492088,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0005,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.005156537753222836,
512
+ "grad_norm": 0.021368781104683876,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.0004,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.005230202578268877,
519
+ "grad_norm": 0.02990240976214409,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.0008,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.005303867403314917,
526
+ "grad_norm": 0.006831527221947908,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0003,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.005377532228360958,
533
+ "grad_norm": 0.012739215977489948,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0002,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.005451197053406998,
540
+ "grad_norm": 0.00279725668951869,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.0001,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0055248618784530384,
547
+ "grad_norm": 0.02894754707813263,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.0005,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.005598526703499079,
554
+ "grad_norm": 0.022462375462055206,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.0003,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.00567219152854512,
561
+ "grad_norm": 0.021344490349292755,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0005,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.00574585635359116,
568
+ "grad_norm": 0.03600762411952019,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0005,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.005819521178637201,
575
+ "grad_norm": 0.01306220330297947,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0002,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.005893186003683241,
582
+ "grad_norm": 0.0199806559830904,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.0002,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.0059668508287292815,
589
+ "grad_norm": 0.008712571114301682,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.0002,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.006040515653775323,
596
+ "grad_norm": 0.0022454585414379835,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0001,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.006114180478821363,
603
+ "grad_norm": 0.0017042462714016438,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.0001,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0061878453038674034,
610
+ "grad_norm": 0.007450164295732975,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0002,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.006261510128913444,
617
+ "grad_norm": 0.00840887799859047,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0002,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.006335174953959484,
624
+ "grad_norm": 0.02648269385099411,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0003,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.0064088397790055245,
631
+ "grad_norm": 0.002491602674126625,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0001,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.006482504604051566,
638
+ "grad_norm": 0.006651001516729593,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0002,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.006556169429097606,
645
+ "grad_norm": 0.006767287850379944,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0002,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0066298342541436465,
652
+ "grad_norm": 0.0055321455001831055,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0001,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.006703499079189687,
659
+ "grad_norm": 0.19037975370883942,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0013,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.006777163904235727,
666
+ "grad_norm": 0.098416768014431,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0008,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.006850828729281768,
673
+ "grad_norm": 0.5576754212379456,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0123,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.006924493554327809,
680
+ "grad_norm": 0.21522895991802216,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0022,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.006998158379373849,
687
+ "grad_norm": 0.09357759356498718,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0006,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.0070718232044198895,
694
+ "grad_norm": 0.004402390215545893,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0001,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.00714548802946593,
701
+ "grad_norm": 0.04337269440293312,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0007,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.00721915285451197,
708
+ "grad_norm": 0.0028723084833472967,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0001,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0072928176795580115,
715
+ "grad_norm": 0.009090679697692394,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0002,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.007366482504604052,
722
+ "grad_norm": 0.008667516522109509,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0002,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.007366482504604052,
729
+ "eval_loss": 0.0033941082656383514,
730
+ "eval_runtime": 1802.122,
731
+ "eval_samples_per_second": 12.687,
732
+ "eval_steps_per_second": 3.172,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5763966897894195e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null