aleegis11 commited on
Commit
b54be13
·
verified ·
1 Parent(s): 16de016

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 sha256:581c5e7e3322cf0122f4255df7553cb11c1b3cb308c92c2dc5036b71ad8e86ff
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f989056a76a20f7b28e7372806794fd13007a937cc8cba570c1b2cba3995db
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c50a6ad4ea4c3556b0b5b3a10874ab288ca28a6ae9c97bd6bcf03c9334815300
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295b128f2544aa2ad7ad248863d44d65d18e52abd5e3965608087a2a573417de
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:d51e57956e11f4eb5777791b07ffdf6e90a5da96de6b26700a5120e78bfff1c5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35712a0ebc49d17156fd6a5a5206fcfc353ce2c2ec1ee245ed86b49e22c38a6a
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": 0.4138473570346832,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.020548648926333093,
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": 13.512,
374
  "eval_steps_per_second": 3.379,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.15499809800192e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3455173075199127,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.041097297852666186,
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": 13.512,
374
  "eval_steps_per_second": 3.379,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.020959621904859754,
379
+ "grad_norm": 12.342080116271973,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.4146,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.021370594883386416,
386
+ "grad_norm": 6.080272197723389,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.8887,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.02178156786191308,
393
+ "grad_norm": 3.8052139282226562,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.5046,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.022192540840439742,
400
+ "grad_norm": 2.571850299835205,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.3564,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.022603513818966404,
407
+ "grad_norm": 2.810466766357422,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.4813,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.023014486797493065,
414
+ "grad_norm": 2.573469877243042,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.3625,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.023425459776019727,
421
+ "grad_norm": 2.7407968044281006,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.4922,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.02383643275454639,
428
+ "grad_norm": 2.315983295440674,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.3607,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.02424740573307305,
435
+ "grad_norm": 2.314702272415161,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.3143,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.02465837871159971,
442
+ "grad_norm": 2.3891677856445312,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.3717,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.025069351690126373,
449
+ "grad_norm": 2.1026391983032227,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.3662,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.025480324668653034,
456
+ "grad_norm": 2.3388073444366455,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.3363,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0258912976471797,
463
+ "grad_norm": 2.0514118671417236,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.1694,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.02630227062570636,
470
+ "grad_norm": 2.41292667388916,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.2284,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.026713243604233022,
477
+ "grad_norm": 2.4270639419555664,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.4271,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.027124216582759684,
484
+ "grad_norm": 2.5759642124176025,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.2959,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.027535189561286345,
491
+ "grad_norm": 2.39304780960083,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.1937,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.027946162539813007,
498
+ "grad_norm": 2.2705135345458984,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.2459,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02835713551833967,
505
+ "grad_norm": 2.4148080348968506,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.2989,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.02876810849686633,
512
+ "grad_norm": 2.030571460723877,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.2639,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02917908147539299,
519
+ "grad_norm": 2.2056310176849365,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.2337,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.029590054453919656,
526
+ "grad_norm": 2.6393370628356934,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.4412,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.030001027432446318,
533
+ "grad_norm": 1.976220965385437,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.2788,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.03041200041097298,
540
+ "grad_norm": 2.2979400157928467,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.3334,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.03082297338949964,
547
+ "grad_norm": 1.8376797437667847,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.2085,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.031233946368026302,
554
+ "grad_norm": 2.161620616912842,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.3036,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.03164491934655297,
561
+ "grad_norm": 1.7936217784881592,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.1837,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.032055892325079625,
568
+ "grad_norm": 2.5552217960357666,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.5987,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03246686530360629,
575
+ "grad_norm": 2.120462656021118,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.2969,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03287783828213295,
582
+ "grad_norm": 1.996077537536621,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.3274,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.03328881126065961,
589
+ "grad_norm": 1.8100478649139404,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.3179,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.03369978423918627,
596
+ "grad_norm": 1.971675992012024,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.3049,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.034110757217712936,
603
+ "grad_norm": 2.0137078762054443,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2078,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.034521730196239594,
610
+ "grad_norm": 2.2327828407287598,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.2199,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.03493270317476626,
617
+ "grad_norm": 2.3494155406951904,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.2796,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.035343676153292924,
624
+ "grad_norm": 1.7998632192611694,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.2157,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.03575464913181958,
631
+ "grad_norm": 2.1565279960632324,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.1824,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.03616562211034625,
638
+ "grad_norm": 2.000291109085083,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.1575,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.036576595088872906,
645
+ "grad_norm": 2.0263590812683105,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.2279,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.03698756806739957,
652
+ "grad_norm": 2.2121741771698,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.1393,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03739854104592623,
659
+ "grad_norm": 1.6476695537567139,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.0791,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.037809514024452893,
666
+ "grad_norm": 2.098963975906372,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.2437,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.03822048700297955,
673
+ "grad_norm": 1.7796459197998047,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.1393,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.038631459981506217,
680
+ "grad_norm": 1.9552690982818604,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.0573,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.039042432960032875,
687
+ "grad_norm": 1.4341356754302979,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.9289,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.03945340593855954,
694
+ "grad_norm": 1.6645524501800537,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.1177,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.039864378917086205,
701
+ "grad_norm": 1.5547387599945068,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.0653,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.04027535189561286,
708
+ "grad_norm": 1.818339467048645,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.0471,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.04068632487413953,
715
+ "grad_norm": 1.5988365411758423,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.9549,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.041097297852666186,
722
+ "grad_norm": 1.8590444326400757,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.9896,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.041097297852666186,
729
+ "eval_loss": 0.3455173075199127,
730
+ "eval_runtime": 303.2543,
731
+ "eval_samples_per_second": 13.517,
732
+ "eval_steps_per_second": 3.38,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null