abaddon182 commited on
Commit
cb27648
·
verified ·
1 Parent(s): 978ac56

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:e834fc39aa57326743839d37570507fa402239691ce48042c02dfede60dab7b6
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffdc92054962c9e76f1e40124b36899d7cf80363ac4d2f5725116cb7a133f6d
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6483e395488d9c8d1bdd92f25d086bde159f6162c9c9860019fec05dc97dfc02
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ed42100f987336f4165f5d4b79406e1d8005fce4b19b133a6700eaca408f22
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:267e9f9478460251b52571da1a6253f383a04680955606f0b2752f0d31d5b7da
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80280779ecf9f0a34fc2db12744ebce084f97b9b49c32491ec6b3a7309b7a51d
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": 2.3259637355804443,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.029359953024075163,
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": 13.491,
374
  "eval_steps_per_second": 3.373,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.322726729515008e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.288942575454712,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.058719906048150326,
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": 13.491,
374
  "eval_steps_per_second": 3.373,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.029947152084556665,
379
+ "grad_norm": 0.4676729738712311,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.3446,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.030534351145038167,
386
+ "grad_norm": 0.7390397787094116,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.7258,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.031121550205519672,
393
+ "grad_norm": 0.5213898420333862,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.275,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.031708749266001174,
400
+ "grad_norm": 0.4595617949962616,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.3287,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03229594832648268,
407
+ "grad_norm": 0.3932957947254181,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.1543,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.03288314738696418,
414
+ "grad_norm": 0.37599682807922363,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.3102,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03347034644744568,
421
+ "grad_norm": 0.40485823154449463,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.2687,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.03405754550792719,
428
+ "grad_norm": 0.3882083594799042,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.3044,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.03464474456840869,
435
+ "grad_norm": 0.37490957975387573,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.294,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03523194362889019,
442
+ "grad_norm": 0.3471771776676178,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.1857,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.0358191426893717,
449
+ "grad_norm": 0.441429078578949,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.2638,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0364063417498532,
456
+ "grad_norm": 0.44914543628692627,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.4695,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0369935408103347,
463
+ "grad_norm": 0.44081437587738037,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.221,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.037580739870816206,
470
+ "grad_norm": 0.48773181438446045,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.4275,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.03816793893129771,
477
+ "grad_norm": 0.45748454332351685,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.3778,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.038755137991779216,
484
+ "grad_norm": 0.3910389542579651,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.236,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.039342337052260715,
491
+ "grad_norm": 0.45711007714271545,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.2863,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.03992953611274222,
498
+ "grad_norm": 0.4611903131008148,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.2532,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.040516735173223725,
505
+ "grad_norm": 0.4584813117980957,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.8862,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.041103934233705224,
512
+ "grad_norm": 0.4744361340999603,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.0616,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04169113329418673,
519
+ "grad_norm": 0.4039895832538605,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.1366,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.042278332354668234,
526
+ "grad_norm": 0.43253761529922485,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.1594,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.04286553141514973,
533
+ "grad_norm": 0.5091691017150879,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.1627,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04345273047563124,
540
+ "grad_norm": 0.4764954745769501,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.1508,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04403992953611274,
547
+ "grad_norm": 0.49679040908813477,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.284,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.04462712859659425,
554
+ "grad_norm": 0.5358265042304993,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.331,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.04521432765707575,
561
+ "grad_norm": 0.5226441025733948,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.2219,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.04580152671755725,
568
+ "grad_norm": 0.5147382616996765,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.9872,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.04638872577803876,
575
+ "grad_norm": 0.5225254893302917,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.0704,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.046975924838520255,
582
+ "grad_norm": 0.5500540137290955,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.2335,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.04756312389900176,
589
+ "grad_norm": 0.5460954308509827,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.3627,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.048150322959483266,
596
+ "grad_norm": 0.5873216986656189,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.0461,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.04873752201996477,
603
+ "grad_norm": 0.5911714434623718,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.2967,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.04932472108044627,
610
+ "grad_norm": 0.5971319675445557,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.3029,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.049911920140927775,
617
+ "grad_norm": 0.644014298915863,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.3323,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.05049911920140928,
624
+ "grad_norm": 0.6283090710639954,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.2745,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.05108631826189078,
631
+ "grad_norm": 0.6029326319694519,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.4444,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.051673517322372284,
638
+ "grad_norm": 0.6873989701271057,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.3448,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.05226071638285379,
645
+ "grad_norm": 0.6990385055541992,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.3652,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.05284791544333529,
652
+ "grad_norm": 0.6101760864257812,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.1092,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.05343511450381679,
659
+ "grad_norm": 0.6388440132141113,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.3159,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.0540223135642983,
666
+ "grad_norm": 0.707058310508728,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.3384,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0546095126247798,
673
+ "grad_norm": 0.7057024836540222,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.2795,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0551967116852613,
680
+ "grad_norm": 0.691746175289154,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.3113,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.05578391074574281,
687
+ "grad_norm": 0.8184278011322021,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.349,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.05637110980622431,
694
+ "grad_norm": 0.7519662976264954,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.5017,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.05695830886670581,
701
+ "grad_norm": 0.7975960373878479,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.1257,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.057545507927187316,
708
+ "grad_norm": 0.9032453298568726,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.5218,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.05813270698766882,
715
+ "grad_norm": 1.034710168838501,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.2292,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.058719906048150326,
722
+ "grad_norm": 1.1983397006988525,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.5094,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.058719906048150326,
729
+ "eval_loss": 2.288942575454712,
730
+ "eval_runtime": 212.8731,
731
+ "eval_samples_per_second": 13.473,
732
+ "eval_steps_per_second": 3.368,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4716547893297152e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null