ancient41 commited on
Commit
c4084ae
·
verified ·
1 Parent(s): 45b20af

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 sha256:8956252153c144b29e4d4e14cc89eb37f069b03262f8c6b10740897cfae0682f
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b2c5d629481b018f17da6aaa530859dd84823bf447d9e31b7c96ad205c2f11d
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e191e3f1d67743e4dbb879cd05d4c457f11d5c094b2da3a57188d9585634a958
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a8ed22524d003781b3c10588038f67040bb9c7a1960c090591f532a8ecad0bc
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3d53e3c534fbe3dc2e049fcff9820ab696b39da34f0948d1c77565478d093a7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e1dc17e7a3bfc808fd81f6d6f871582b3248596002b5607726dd2bf9b91cac
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": 1.4570739269256592,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.00704324552753909,
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": 49.736,
374
  "eval_steps_per_second": 12.437,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.0719067958673408e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0559614896774292,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.01408649105507818,
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": 49.736,
374
  "eval_steps_per_second": 12.437,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.007184110438089872,
379
+ "grad_norm": 11.111729621887207,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.4741,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.007324975348640654,
386
+ "grad_norm": 9.560843467712402,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.4055,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.007465840259191435,
393
+ "grad_norm": 5.6692280769348145,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.2072,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.007606705169742217,
400
+ "grad_norm": 3.938448190689087,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.0505,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.007747570080292999,
407
+ "grad_norm": 2.66489315032959,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.8585,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.00788843499084378,
414
+ "grad_norm": 1.8790820837020874,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.823,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.008029299901394563,
421
+ "grad_norm": 2.0918898582458496,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.8211,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.008170164811945345,
428
+ "grad_norm": 2.090571165084839,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.5641,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.008311029722496126,
435
+ "grad_norm": 2.2309327125549316,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.728,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.008451894633046908,
442
+ "grad_norm": 1.7858821153640747,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.699,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.00859275954359769,
449
+ "grad_norm": 1.542462706565857,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.4813,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.008733624454148471,
456
+ "grad_norm": 1.2382235527038574,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.4708,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.008874489364699253,
463
+ "grad_norm": 1.4558863639831543,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.1363,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.009015354275250036,
470
+ "grad_norm": 1.6121326684951782,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.0638,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.009156219185800818,
477
+ "grad_norm": 1.290604829788208,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 0.9822,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0092970840963516,
484
+ "grad_norm": 1.4775842428207397,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.1594,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.00943794900690238,
491
+ "grad_norm": 1.4290190935134888,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 0.8742,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.009578813917453162,
498
+ "grad_norm": 1.162203073501587,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 0.7075,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.009719678828003944,
505
+ "grad_norm": 1.4816632270812988,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 0.8478,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.009860543738554725,
512
+ "grad_norm": 1.1275964975357056,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 0.7481,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.010001408649105507,
519
+ "grad_norm": 1.0901832580566406,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 0.771,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.01014227355965629,
526
+ "grad_norm": 1.3845051527023315,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 0.8662,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.010283138470207072,
533
+ "grad_norm": 1.2006878852844238,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 0.5596,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.010424003380757853,
540
+ "grad_norm": 1.6490373611450195,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 0.8285,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.010564868291308635,
547
+ "grad_norm": 1.2739609479904175,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 0.6566,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.010705733201859417,
554
+ "grad_norm": 1.1623024940490723,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 0.6666,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.010846598112410198,
561
+ "grad_norm": 1.4328917264938354,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 0.5614,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.01098746302296098,
568
+ "grad_norm": 1.2306725978851318,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 0.5582,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.011128327933511763,
575
+ "grad_norm": 1.353375792503357,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 0.6759,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.011269192844062545,
582
+ "grad_norm": 1.295104742050171,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 0.6997,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.011410057754613326,
589
+ "grad_norm": 1.742098331451416,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 0.6682,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.011550922665164108,
596
+ "grad_norm": 1.1515581607818604,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 0.5445,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.01169178757571489,
603
+ "grad_norm": 1.251039981842041,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 0.3921,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.011832652486265671,
610
+ "grad_norm": 1.612655520439148,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 0.7296,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.011973517396816452,
617
+ "grad_norm": 1.2194619178771973,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.5372,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.012114382307367234,
624
+ "grad_norm": 1.538738489151001,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 0.5495,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.012255247217918017,
631
+ "grad_norm": 1.1339927911758423,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.4999,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.012396112128468799,
638
+ "grad_norm": 1.3610646724700928,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.6225,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.01253697703901958,
645
+ "grad_norm": 1.2226330041885376,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.4756,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.012677841949570362,
652
+ "grad_norm": 1.316048264503479,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.5727,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.012818706860121144,
659
+ "grad_norm": 1.595350980758667,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.0199,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.012959571770671925,
666
+ "grad_norm": 1.6149495840072632,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.8526,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.013100436681222707,
673
+ "grad_norm": 1.4621623754501343,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.5669,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.01324130159177349,
680
+ "grad_norm": 1.6394346952438354,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.8591,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.013382166502324272,
687
+ "grad_norm": 2.0890185832977295,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.1071,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.013523031412875053,
694
+ "grad_norm": 1.8629014492034912,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.1249,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.013663896323425835,
701
+ "grad_norm": 2.2603368759155273,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.3536,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.013804761233976616,
708
+ "grad_norm": 2.8389956951141357,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.5428,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.013945626144527398,
715
+ "grad_norm": 4.9247589111328125,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.1399,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.01408649105507818,
722
+ "grad_norm": 6.604344367980957,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.5073,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.01408649105507818,
729
+ "eval_loss": 1.0559614896774292,
730
+ "eval_runtime": 240.4752,
731
+ "eval_samples_per_second": 49.722,
732
+ "eval_steps_per_second": 12.434,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.1438135917346816e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null