0x1202 commited on
Commit
0e19baa
·
verified ·
1 Parent(s): 40bf78c

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 sha256:476dc07bc5da0eb4d99915a53ba7fbd7778e313ce0f5416cfaf4f920eb0d421b
3
  size 239906848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9fa2ff246ac17497e2a8ec383e3f5b8b3409950d836c8ebf74fcfdae773ed5
3
  size 239906848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:179c486469a06cda11b7b1a676594b7d3e5aaf89a8ccc276ef9de4299f6fe3b1
3
  size 122200212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77e5f4d02461c36f61863d91a7fdd3df17b83219e120b23befcf385c38e70b3
3
  size 122200212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c542f8df8925b424c52e5265a0d773b9aaaa4d8743117e2000401f92ae3f33c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f05dc69ef0bffac0c7dad05d40261f8cc7fadec7a2b18286685c393506d06c9
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": 0.12350469827651978,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.5420054200542005,
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": 42.186,
374
  "eval_steps_per_second": 10.546,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.317128896512e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.09879136830568314,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.084010840108401,
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": 42.186,
374
  "eval_steps_per_second": 10.546,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5528455284552846,
379
+ "grad_norm": 0.5761507153511047,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 0.1187,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.5636856368563685,
386
+ "grad_norm": 0.6159778237342834,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.0727,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.5745257452574526,
393
+ "grad_norm": 0.8006864786148071,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 0.0819,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.5853658536585366,
400
+ "grad_norm": 0.7325972318649292,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.1168,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.5962059620596206,
407
+ "grad_norm": 0.6329816579818726,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.1117,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.6070460704607046,
414
+ "grad_norm": 0.8424084186553955,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 0.093,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.6178861788617886,
421
+ "grad_norm": 0.6663784980773926,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 0.1303,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.6287262872628726,
428
+ "grad_norm": 0.523448646068573,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.0914,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.6395663956639567,
435
+ "grad_norm": 0.7643095254898071,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.1144,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.6504065040650406,
442
+ "grad_norm": 0.4949480891227722,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 0.0521,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.6612466124661247,
449
+ "grad_norm": 0.6844000220298767,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 0.1302,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.6720867208672087,
456
+ "grad_norm": 0.6087970733642578,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 0.0696,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.6829268292682927,
463
+ "grad_norm": 0.6328505277633667,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 0.1631,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.6937669376693767,
470
+ "grad_norm": 0.7826113104820251,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.174,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.7046070460704607,
477
+ "grad_norm": 0.7086710333824158,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.1047,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.7154471544715447,
484
+ "grad_norm": 0.5617452263832092,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 0.0978,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.7262872628726287,
491
+ "grad_norm": 0.5778073668479919,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.0718,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.7371273712737128,
498
+ "grad_norm": 0.836530327796936,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.0869,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.7479674796747967,
505
+ "grad_norm": 0.9944505095481873,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.1184,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.7588075880758808,
512
+ "grad_norm": 0.4123961627483368,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.1155,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.7696476964769647,
519
+ "grad_norm": 0.4990311563014984,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.0938,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.7804878048780488,
526
+ "grad_norm": 0.28021708130836487,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.0481,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.7913279132791328,
533
+ "grad_norm": 0.4944506585597992,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.146,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.8021680216802168,
540
+ "grad_norm": 0.7031269669532776,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.1715,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.8130081300813008,
547
+ "grad_norm": 0.4086264371871948,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.1055,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.8238482384823849,
554
+ "grad_norm": 0.33718255162239075,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.0451,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.8346883468834688,
561
+ "grad_norm": 0.4637962877750397,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.0806,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.8455284552845529,
568
+ "grad_norm": 0.5173426866531372,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.0526,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.8563685636856369,
575
+ "grad_norm": 0.44306081533432007,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.0655,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.8672086720867209,
582
+ "grad_norm": 0.7521052360534668,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.1433,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.8780487804878049,
589
+ "grad_norm": 0.5706959962844849,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.0591,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.8888888888888888,
596
+ "grad_norm": 0.46802663803100586,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.0467,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.8997289972899729,
603
+ "grad_norm": 0.711159348487854,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.0826,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.9105691056910569,
610
+ "grad_norm": 0.813417375087738,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.1174,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.9214092140921409,
617
+ "grad_norm": 0.677147626876831,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.139,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.9322493224932249,
624
+ "grad_norm": 0.41531622409820557,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.0284,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.943089430894309,
631
+ "grad_norm": 0.3974713683128357,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.0475,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.9539295392953929,
638
+ "grad_norm": 0.6932405829429626,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.0966,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.964769647696477,
645
+ "grad_norm": 0.386869877576828,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.0464,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.975609756097561,
652
+ "grad_norm": 0.8761130571365356,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.1191,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.986449864498645,
659
+ "grad_norm": 0.5070018768310547,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.029,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.997289972899729,
666
+ "grad_norm": 1.7458750009536743,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.1672,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.008130081300813,
673
+ "grad_norm": 1.0867496728897095,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.1955,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.018970189701897,
680
+ "grad_norm": 0.27728036046028137,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0539,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.029810298102981,
687
+ "grad_norm": 0.23874682188034058,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.0637,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.040650406504065,
694
+ "grad_norm": 0.15150757133960724,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0186,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.051490514905149,
701
+ "grad_norm": 0.35452330112457275,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.0713,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.062330623306233,
708
+ "grad_norm": 0.549517035484314,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.0866,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.0731707317073171,
715
+ "grad_norm": 0.44955000281333923,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.0723,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.084010840108401,
722
+ "grad_norm": 0.3139077425003052,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.0249,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.084010840108401,
729
+ "eval_loss": 0.09879136830568314,
730
+ "eval_runtime": 3.6916,
731
+ "eval_samples_per_second": 42.258,
732
+ "eval_steps_per_second": 10.565,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.634257793024e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null