prxy5607 commited on
Commit
6f026c0
·
verified ·
1 Parent(s): 41ec4ab

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:b859ae5de08c3f22c1b3545e13858abbe9fd142d36f8f2477997a60979a01e38
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7168846f2f1baec4443d6cd9497f6f24b334ae2856cfa7abbc424626256d7b34
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf0492c6deee64d4efe9f70d74434c803d4fdadd287d52483e82156d527d7cba
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e7cf23ee24530205a1865faae7929f22725257be79c2b07e6f6d4781ae5ecb
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:ab631dbaf427223d65527f57219703464d850709cf1e39b4eace385d103f9f1b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38143ff60d2863c80e862df55e788ad092450cce502d1a565fb0a59eb3e0f1d6
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": 0.005221195053309202,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.008027614995584811,
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": 51.264,
374
  "eval_steps_per_second": 12.818,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 4327950161805312.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.003659700509160757,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.016055229991169623,
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": 51.264,
374
  "eval_steps_per_second": 12.818,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.008188167295496507,
379
+ "grad_norm": 0.5250939130783081,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.1255,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.008348719595408205,
386
+ "grad_norm": 0.057992178946733475,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.0009,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0085092718953199,
393
+ "grad_norm": 0.04958822950720787,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.0016,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.008669824195231596,
400
+ "grad_norm": 0.05028170347213745,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.0008,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.008830376495143294,
407
+ "grad_norm": 0.09673178941011429,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.0019,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.00899092879505499,
414
+ "grad_norm": 0.0684753954410553,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.0083,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.009151481094966685,
421
+ "grad_norm": 0.08950470387935638,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.0012,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.00931203339487838,
428
+ "grad_norm": 0.05458079278469086,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0013,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.009472585694790078,
435
+ "grad_norm": 0.079529769718647,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.001,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.009633137994701774,
442
+ "grad_norm": 0.03740987554192543,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.0007,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.00979369029461347,
449
+ "grad_norm": 0.047025859355926514,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.0016,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.009954242594525167,
456
+ "grad_norm": 0.03502329811453819,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0007,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.010114794894436863,
463
+ "grad_norm": 0.05259818583726883,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.0009,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.010275347194348559,
470
+ "grad_norm": 0.013502693735063076,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.0004,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.010435899494260254,
477
+ "grad_norm": 0.025728760287165642,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0011,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.010596451794171952,
484
+ "grad_norm": 0.02178327552974224,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.0006,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.010757004094083648,
491
+ "grad_norm": 0.06834480166435242,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0004,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.010917556393995343,
498
+ "grad_norm": 0.051519911736249924,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0003,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.011078108693907041,
505
+ "grad_norm": 0.019947610795497894,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0003,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.011238660993818737,
512
+ "grad_norm": 0.02443559840321541,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.0004,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.011399213293730432,
519
+ "grad_norm": 0.11091884970664978,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.0006,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.011559765593642128,
526
+ "grad_norm": 0.005004688631743193,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0001,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.011720317893553826,
533
+ "grad_norm": 0.012527952902019024,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0002,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.011880870193465521,
540
+ "grad_norm": 0.020513156428933144,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.0001,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.012041422493377217,
547
+ "grad_norm": 0.0047658514231443405,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.0001,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.012201974793288915,
554
+ "grad_norm": 0.009428201243281364,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.0001,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.01236252709320061,
561
+ "grad_norm": 0.06915072351694107,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0007,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.012523079393112306,
568
+ "grad_norm": 0.016525782644748688,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0002,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.012683631693024002,
575
+ "grad_norm": 0.05866200849413872,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0015,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0128441839929357,
582
+ "grad_norm": 0.00698102219030261,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.0001,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.013004736292847395,
589
+ "grad_norm": 0.01773742213845253,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.0002,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.01316528859275909,
596
+ "grad_norm": 0.0217452272772789,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0001,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.013325840892670788,
603
+ "grad_norm": 0.04312044009566307,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.001,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.013486393192582484,
610
+ "grad_norm": 0.004618401639163494,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0001,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.01364694549249418,
617
+ "grad_norm": 0.08741449564695358,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0003,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.013807497792405875,
624
+ "grad_norm": 0.003669846337288618,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0001,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.013968050092317573,
631
+ "grad_norm": 0.004791214596480131,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0001,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.014128602392229269,
638
+ "grad_norm": 0.052703697234392166,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0002,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.014289154692140964,
645
+ "grad_norm": 0.002884466666728258,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.014449706992052662,
652
+ "grad_norm": 0.0029359045438468456,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0001,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.014610259291964358,
659
+ "grad_norm": 0.03336722031235695,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0003,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.014770811591876053,
666
+ "grad_norm": 0.012027747929096222,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0002,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.014931363891787749,
673
+ "grad_norm": 0.11303514987230301,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0008,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.015091916191699447,
680
+ "grad_norm": 0.002124216640368104,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0001,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.015252468491611142,
687
+ "grad_norm": 0.2330835610628128,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0003,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.015413020791522838,
694
+ "grad_norm": 0.001057187793776393,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.015573573091434536,
701
+ "grad_norm": 0.0015783881535753608,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.01573412539134623,
708
+ "grad_norm": 0.3883363604545593,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0008,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.01589467769125793,
715
+ "grad_norm": 0.004075345583260059,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0001,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.016055229991169623,
722
+ "grad_norm": 0.24348968267440796,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0028,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.016055229991169623,
729
+ "eval_loss": 0.003659700509160757,
730
+ "eval_runtime": 205.4097,
731
+ "eval_samples_per_second": 51.069,
732
+ "eval_steps_per_second": 12.77,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 8617257911451648.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null