prxy5605 commited on
Commit
7d28964
·
verified ·
1 Parent(s): 4461d82

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 sha256:14a535220b48aeb358acdca9b9c6f40897ffbe8e0212e7665b9048fad4a8e2a9
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5b1abf5bd345ca9269b6678fa4ff36f4ec293bce2558fcfad36f785285e5855
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f8cca963a000b5f228945ba8ec6a38e0bc69f12dda66c0d25a65e33e85e7cd1
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136a1520d955f78f466d607f76c06f1760d8bc3400979e1003574d3b1284ac46
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:100bf918095c2a0a8f8be5f3f7c8c03ed85aa437eabea3b681dc7fb5511f77a8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:146a62c8de7ccf0512b0d08844287d2ffbb8a8a610d9d25c830a5dc5edc02c22
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": 5.708453318220563e-05,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.6472491909385113,
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": 13.251,
374
  "eval_steps_per_second": 3.364,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.54256789372928e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.6809143491846044e-06,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.2944983818770226,
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": 13.251,
374
  "eval_steps_per_second": 3.364,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.6601941747572816,
379
+ "grad_norm": 0.5545428395271301,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.0024,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.6731391585760518,
386
+ "grad_norm": 0.0015667704865336418,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.0,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.686084142394822,
393
+ "grad_norm": 0.011077708564698696,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.0,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.6990291262135923,
400
+ "grad_norm": 0.010326799936592579,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.0,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.7119741100323624,
407
+ "grad_norm": 0.0014523833524435759,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.0,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.7249190938511327,
414
+ "grad_norm": 0.06251269578933716,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.0002,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.7378640776699029,
421
+ "grad_norm": 0.003645202610641718,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.0,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.7508090614886731,
428
+ "grad_norm": 0.2278345227241516,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0013,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.7637540453074434,
435
+ "grad_norm": 0.003915652632713318,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.0,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.7766990291262136,
442
+ "grad_norm": 0.0031239991076290607,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.0,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.7896440129449838,
449
+ "grad_norm": 0.006219485308974981,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.0001,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.8025889967637541,
456
+ "grad_norm": 0.005084617529064417,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.8155339805825242,
463
+ "grad_norm": 0.003509129863232374,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.0,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.8284789644012945,
470
+ "grad_norm": 0.0037375520914793015,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.0,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.8414239482200647,
477
+ "grad_norm": 0.00264919875189662,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.0,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.8543689320388349,
484
+ "grad_norm": 0.10307146608829498,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.0002,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.8673139158576052,
491
+ "grad_norm": 0.001447496935725212,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.8802588996763754,
498
+ "grad_norm": 0.0005993408849462867,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.8932038834951457,
505
+ "grad_norm": 0.0018503112951293588,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.0,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.9061488673139159,
512
+ "grad_norm": 0.0011176472762599587,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.0,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.919093851132686,
519
+ "grad_norm": 0.0071342382580041885,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.0,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.9320388349514563,
526
+ "grad_norm": 0.0045208255760371685,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.9449838187702265,
533
+ "grad_norm": 0.0016186069697141647,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.0,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.9579288025889967,
540
+ "grad_norm": 0.0014599431306123734,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.0,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.970873786407767,
547
+ "grad_norm": 0.0028509364929050207,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.0,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.9838187702265372,
554
+ "grad_norm": 0.0015371855115517974,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.0,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.9967637540453075,
561
+ "grad_norm": 0.0928664579987526,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0001,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.0097087378640777,
568
+ "grad_norm": 0.0019110508728772402,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.022653721682848,
575
+ "grad_norm": 0.0001286536717088893,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.035598705501618,
582
+ "grad_norm": 0.00010072574514197186,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.0,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.0485436893203883,
589
+ "grad_norm": 8.10532656032592e-05,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.0,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.0614886731391586,
596
+ "grad_norm": 0.00010899638436967507,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.074433656957929,
603
+ "grad_norm": 7.373379776254296e-05,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.0,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.087378640776699,
610
+ "grad_norm": 0.00044416377204470336,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.0,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.1003236245954693,
617
+ "grad_norm": 0.00014110577467363328,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.0,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.1132686084142396,
624
+ "grad_norm": 7.416921289404854e-05,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.1262135922330097,
631
+ "grad_norm": 6.953041884116828e-05,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.13915857605178,
638
+ "grad_norm": 0.00018072547391057014,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.1521035598705502,
645
+ "grad_norm": 0.00014231581008061767,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.1650485436893203,
652
+ "grad_norm": 0.049870043992996216,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0001,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.1779935275080906,
659
+ "grad_norm": 7.035312592051923e-05,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.190938511326861,
666
+ "grad_norm": 0.00027099126600660384,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.0,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.203883495145631,
673
+ "grad_norm": 0.00015066895866766572,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.2168284789644013,
680
+ "grad_norm": 0.0002044395951088518,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.2297734627831716,
687
+ "grad_norm": 0.00016389232769142836,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.2427184466019416,
694
+ "grad_norm": 0.00033923389855772257,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.255663430420712,
701
+ "grad_norm": 0.00017732290143612772,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.2686084142394822,
708
+ "grad_norm": 0.010200129821896553,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.2815533980582523,
715
+ "grad_norm": 0.00042962911538779736,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.2944983818770226,
722
+ "grad_norm": 0.0004276715044397861,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.2944983818770226,
729
+ "eval_loss": 2.6809143491846044e-06,
730
+ "eval_runtime": 9.7982,
731
+ "eval_samples_per_second": 13.268,
732
+ "eval_steps_per_second": 3.368,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.50757075775914e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null