beast33 commited on
Commit
124702f
·
verified ·
1 Parent(s): 7e0da51

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:a5614e311b4abd529922f774317f95ddfd5b8e8a0da72edbc0a1b283df2c28b9
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45127b73e3b27fc338bd681520d93c8773a25cdb018f642911487f0985906776
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:172931690dd6647d90b5682372a0cfc0248dfedd9daf5224ef9dc55341c7a7b1
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5b8c4810f46d31a93005728373c1ed65535ffe41d1c70ad892b199eeaad275
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e81463f89295e06321c3b625af92889aa1a851658202eadc558f323b0bed38ce
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f94d36ef3ab9dc9680e65ee6fa2913a95bb7a0076ced404018c69d5213c07afd
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": 1.054203987121582,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.032509752925877766,
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": 9.011,
374
  "eval_steps_per_second": 2.254,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.144990643847168e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0209071636199951,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06501950585175553,
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": 9.011,
374
  "eval_steps_per_second": 2.254,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03315994798439532,
379
+ "grad_norm": 0.3386886715888977,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.0257,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.033810143042912875,
386
+ "grad_norm": 0.3361884355545044,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 0.9614,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.03446033810143043,
393
+ "grad_norm": 0.3084128499031067,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.0583,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.035110533159947985,
400
+ "grad_norm": 0.2674861550331116,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 0.9485,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03576072821846554,
407
+ "grad_norm": 0.24764272570610046,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 0.948,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.036410923276983094,
414
+ "grad_norm": 0.24586255848407745,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.0632,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03706111833550065,
421
+ "grad_norm": 0.23815371096134186,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.0403,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0377113133940182,
428
+ "grad_norm": 0.24708771705627441,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 0.9634,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03836150845253576,
435
+ "grad_norm": 0.2594657242298126,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 0.9434,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03901170351105332,
442
+ "grad_norm": 0.2581363916397095,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.0236,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.03966189856957087,
449
+ "grad_norm": 0.28572535514831543,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.0167,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04031209362808843,
456
+ "grad_norm": 0.27552080154418945,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.0812,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04096228868660598,
463
+ "grad_norm": 0.2638622522354126,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.0145,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.04161248374512354,
470
+ "grad_norm": 0.28032687306404114,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 0.9644,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04226267880364109,
477
+ "grad_norm": 0.2831994891166687,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.0199,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.04291287386215865,
484
+ "grad_norm": 0.2876667380332947,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.0307,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.043563068920676205,
491
+ "grad_norm": 0.30388614535331726,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0459,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.044213263979193757,
498
+ "grad_norm": 0.30665335059165955,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.005,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.044863459037711315,
505
+ "grad_norm": 0.3081737160682678,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.9645,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.045513654096228866,
512
+ "grad_norm": 0.34367161989212036,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.1134,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.046163849154746424,
519
+ "grad_norm": 0.3611394762992859,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.0236,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04681404421326398,
526
+ "grad_norm": 0.3540930449962616,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.015,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.04746423927178153,
533
+ "grad_norm": 0.3631446361541748,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.0907,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04811443433029909,
540
+ "grad_norm": 0.3827061057090759,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.9582,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04876462938881664,
547
+ "grad_norm": 0.37133488059043884,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.9584,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.0494148244473342,
554
+ "grad_norm": 0.4201424717903137,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.1141,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.05006501950585176,
561
+ "grad_norm": 0.446561723947525,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.04,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.05071521456436931,
568
+ "grad_norm": 0.45327770709991455,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.911,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.05136540962288687,
575
+ "grad_norm": 0.488609254360199,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.9535,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05201560468140442,
582
+ "grad_norm": 0.5082444548606873,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.9659,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05266579973992198,
589
+ "grad_norm": 0.5167144536972046,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.8035,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.053315994798439535,
596
+ "grad_norm": 0.7916758060455322,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.9813,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.053966189856957086,
603
+ "grad_norm": 0.6592386364936829,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.9619,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.054616384915474644,
610
+ "grad_norm": 0.6843824982643127,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.9291,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.055266579973992196,
617
+ "grad_norm": 0.7502142190933228,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.9775,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.055916775032509754,
624
+ "grad_norm": 0.7345762252807617,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.9682,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.056566970091027305,
631
+ "grad_norm": 1.0729334354400635,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.1668,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.05721716514954486,
638
+ "grad_norm": 0.9465899467468262,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.066,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.05786736020806242,
645
+ "grad_norm": 0.8934149146080017,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.0943,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.05851755526657997,
652
+ "grad_norm": 0.8732466101646423,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.8848,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.05916775032509753,
659
+ "grad_norm": 1.4022270441055298,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.0353,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.05981794538361508,
666
+ "grad_norm": 1.1805094480514526,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.0968,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06046814044213264,
673
+ "grad_norm": 1.171386957168579,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.967,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0611183355006502,
680
+ "grad_norm": 1.0938076972961426,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.843,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.06176853055916775,
687
+ "grad_norm": 1.217340111732483,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.0096,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.06241872561768531,
694
+ "grad_norm": 1.255969762802124,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.9087,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06306892067620286,
701
+ "grad_norm": 1.2926132678985596,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.8561,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.06371911573472042,
708
+ "grad_norm": 1.38904869556427,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.8413,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.06436931079323797,
715
+ "grad_norm": 1.2619047164916992,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.7125,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06501950585175553,
722
+ "grad_norm": 1.9958139657974243,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.9771,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06501950585175553,
729
+ "eval_loss": 1.0209071636199951,
730
+ "eval_runtime": 287.4426,
731
+ "eval_samples_per_second": 9.014,
732
+ "eval_steps_per_second": 2.254,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4254434070560768e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null