nttx commited on
Commit
212eb11
·
verified ·
1 Parent(s): 64b24a8

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 sha256:44a61aa92678aabf723685dff3a6388aa2860c69d2bc7bbc4a8d84deaf487eff
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f45713302ffec12ebb2045b50d0cecf78642afd3c89aacdf6b30270246255740
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fbd367cf7947b43167437f2e62cd460a2008fc746b3b49fc95a6956f1f58f26
3
  size 148047722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3351837ef943841bac25b40343357818d25708f06bc8ead49494dd562f0c62d7
3
  size 148047722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d58be2bfdf572e7fb47b3f8f08cc7b53c23946ec1ad88dff89b3ecfd550b4223
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2769c8496c824dfff8aff679240229e055127b4e67ce00f8f0c475f6e539db60
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 11.14814567565918,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.11389521640091116,
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": 31.449,
374
  "eval_steps_per_second": 7.862,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.4499584088735744e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.204195022583008,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.22779043280182232,
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": 31.449,
374
  "eval_steps_per_second": 7.862,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.11617312072892938,
379
+ "grad_norm": 14.492518424987793,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 14.905,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.11845102505694761,
386
+ "grad_norm": 15.138047218322754,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 14.4474,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.12072892938496584,
393
+ "grad_norm": 15.702535629272461,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 15.193,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.12300683371298406,
400
+ "grad_norm": 14.819658279418945,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 15.2334,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.1252847380410023,
407
+ "grad_norm": 14.035573959350586,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 13.193,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.1275626423690205,
414
+ "grad_norm": 12.402682304382324,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 10.859,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.12984054669703873,
421
+ "grad_norm": 11.38323974609375,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 10.0438,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.13211845102505695,
428
+ "grad_norm": 12.060361862182617,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 10.6817,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.13439635535307518,
435
+ "grad_norm": 12.099507331848145,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 10.7362,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.1366742596810934,
442
+ "grad_norm": 12.863167762756348,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 10.3842,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.13895216400911162,
449
+ "grad_norm": 11.783324241638184,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 10.2279,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.14123006833712984,
456
+ "grad_norm": 11.725215911865234,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 10.0699,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.14350797266514806,
463
+ "grad_norm": 11.681756973266602,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 9.8714,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.14578587699316628,
470
+ "grad_norm": 11.722614288330078,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 10.2099,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.1480637813211845,
477
+ "grad_norm": 11.857827186584473,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 10.0694,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.15034168564920272,
484
+ "grad_norm": 11.467761039733887,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 10.2353,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.15261958997722094,
491
+ "grad_norm": 11.274076461791992,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 10.2479,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.1548974943052392,
498
+ "grad_norm": 11.101469039916992,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 10.4798,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.1571753986332574,
505
+ "grad_norm": 10.9977445602417,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 10.1868,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.15945330296127563,
512
+ "grad_norm": 11.99439525604248,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 10.2214,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.16173120728929385,
519
+ "grad_norm": 11.092779159545898,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 10.2925,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.16400911161731208,
526
+ "grad_norm": 11.094412803649902,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 10.0751,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.1662870159453303,
533
+ "grad_norm": 11.195977210998535,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 10.0356,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.16856492027334852,
540
+ "grad_norm": 11.195873260498047,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 9.7823,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.17084282460136674,
547
+ "grad_norm": 11.247345924377441,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 9.9424,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.17312072892938496,
554
+ "grad_norm": 11.40001106262207,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 9.9038,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.17539863325740318,
561
+ "grad_norm": 11.882497787475586,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 10.0807,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.1776765375854214,
568
+ "grad_norm": 11.732626914978027,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 9.6536,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.17995444191343962,
575
+ "grad_norm": 11.187015533447266,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 9.7543,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.18223234624145787,
582
+ "grad_norm": 11.719953536987305,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 10.0644,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.1845102505694761,
589
+ "grad_norm": 11.316506385803223,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 10.244,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.1867881548974943,
596
+ "grad_norm": 11.08798599243164,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 9.7301,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.18906605922551253,
603
+ "grad_norm": 11.46131706237793,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 9.6195,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.19134396355353075,
610
+ "grad_norm": 11.669816017150879,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 9.6443,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.19362186788154898,
617
+ "grad_norm": 11.048128128051758,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 9.8642,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.1958997722095672,
624
+ "grad_norm": 11.225754737854004,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 9.5736,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.19817767653758542,
631
+ "grad_norm": 11.950643539428711,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 9.8235,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.20045558086560364,
638
+ "grad_norm": 11.37067699432373,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 10.0363,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.20273348519362186,
645
+ "grad_norm": 11.574517250061035,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 9.8055,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.20501138952164008,
652
+ "grad_norm": 11.37779426574707,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 10.0572,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.2072892938496583,
659
+ "grad_norm": 11.561871528625488,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 9.9006,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.20956719817767655,
666
+ "grad_norm": 10.969876289367676,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 9.8471,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.21184510250569477,
673
+ "grad_norm": 11.3236722946167,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 9.7325,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.214123006833713,
680
+ "grad_norm": 10.691644668579102,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 10.0359,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.2164009111617312,
687
+ "grad_norm": 11.637835502624512,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 9.6017,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.21867881548974943,
694
+ "grad_norm": 12.517233848571777,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 10.0366,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.22095671981776766,
701
+ "grad_norm": 11.837146759033203,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 10.1357,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.22323462414578588,
708
+ "grad_norm": 12.083368301391602,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 10.1905,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.2255125284738041,
715
+ "grad_norm": 12.383536338806152,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 10.3541,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.22779043280182232,
722
+ "grad_norm": 14.80471420288086,
723
+ "learning_rate": 0.0,
724
+ "loss": 10.4165,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.22779043280182232,
729
+ "eval_loss": 10.204195022583008,
730
+ "eval_runtime": 23.6586,
731
+ "eval_samples_per_second": 31.278,
732
+ "eval_steps_per_second": 7.82,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.8770571131027456e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null