prxy5605 commited on
Commit
932afea
·
verified ·
1 Parent(s): 2e4a84b

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:bc521a53d16ca93d9458e220df555baeaed779bf04f6ca774b5f66e2984ad3a1
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f105d80e43add9e28cdc56ffe995491a226d4158f6b9f7a3c0e0512990b1e8
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e72c2de745c70540d54d9d4096e0790eaed124fba4a4308117f97717da06371
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17519092f21b83646bc69c019eb3a0a94542756f814a157af23f1e0cdc50a962
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec077984b3ff4536bfc701e3afde445feccaeb8762695a59bef4d7b330c8214f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29cede69602d9069eda91e281a0d5378c703d3311f642430fac3d074099f06ee
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e104b4fac600c8b3fbfec4137aeecd7fcc894137c9c9c8fdc77dbddc73d495f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b50c067469c1b4b6cb25f6ad456ed01667d0d1e466ce910ba4e242673c657c6
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.667975425720215,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 1.1695906432748537,
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": 22.023,
374
  "eval_steps_per_second": 5.506,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.092558531638067e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.5794575214385986,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 2.3391812865497075,
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": 22.023,
374
  "eval_steps_per_second": 5.506,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 1.1929824561403508,
379
+ "grad_norm": 3.982672691345215,
380
+ "learning_rate": 7.346062726185332e-05,
381
+ "loss": 1.9851,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 1.2163742690058479,
386
+ "grad_norm": 4.517981052398682,
387
+ "learning_rate": 7.228691778882693e-05,
388
+ "loss": 1.7932,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 1.239766081871345,
393
+ "grad_norm": 4.8002166748046875,
394
+ "learning_rate": 7.109767620035689e-05,
395
+ "loss": 2.3657,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 1.263157894736842,
400
+ "grad_norm": 2.333965301513672,
401
+ "learning_rate": 6.989373129824604e-05,
402
+ "loss": 2.1879,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 1.286549707602339,
407
+ "grad_norm": 2.5241196155548096,
408
+ "learning_rate": 6.867592213127558e-05,
409
+ "loss": 2.2052,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 1.3099415204678362,
414
+ "grad_norm": 2.5986971855163574,
415
+ "learning_rate": 6.744509741045835e-05,
416
+ "loss": 2.0875,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 1.3333333333333333,
421
+ "grad_norm": 2.735356569290161,
422
+ "learning_rate": 6.62021149175583e-05,
423
+ "loss": 2.2641,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.3567251461988303,
428
+ "grad_norm": 2.861424684524536,
429
+ "learning_rate": 6.494784090728852e-05,
430
+ "loss": 2.1462,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.3801169590643274,
435
+ "grad_norm": 2.953516960144043,
436
+ "learning_rate": 6.368314950360415e-05,
437
+ "loss": 1.9254,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.4035087719298245,
442
+ "grad_norm": 3.429384231567383,
443
+ "learning_rate": 6.240892209051121e-05,
444
+ "loss": 2.0428,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.4269005847953216,
449
+ "grad_norm": 3.717503070831299,
450
+ "learning_rate": 6.112604669781572e-05,
451
+ "loss": 1.6045,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.4502923976608186,
456
+ "grad_norm": 4.62086820602417,
457
+ "learning_rate": 5.983541738224141e-05,
458
+ "loss": 1.5816,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.4736842105263157,
463
+ "grad_norm": 5.065677165985107,
464
+ "learning_rate": 5.853793360434687e-05,
465
+ "loss": 2.1671,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.4970760233918128,
470
+ "grad_norm": 3.0961179733276367,
471
+ "learning_rate": 5.7234499601677026e-05,
472
+ "loss": 2.3001,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.52046783625731,
477
+ "grad_norm": 2.8138766288757324,
478
+ "learning_rate": 5.5926023758585146e-05,
479
+ "loss": 2.272,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.543859649122807,
484
+ "grad_norm": 2.5831410884857178,
485
+ "learning_rate": 5.4613417973165106e-05,
486
+ "loss": 1.9027,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.5672514619883042,
491
+ "grad_norm": 3.276082754135132,
492
+ "learning_rate": 5.329759702173477e-05,
493
+ "loss": 2.3347,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.590643274853801,
498
+ "grad_norm": 3.1773629188537598,
499
+ "learning_rate": 5.197947792131348e-05,
500
+ "loss": 1.9598,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.6140350877192984,
505
+ "grad_norm": 3.4641201496124268,
506
+ "learning_rate": 5.0659979290537954e-05,
507
+ "loss": 1.9397,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.6374269005847952,
512
+ "grad_norm": 3.880099058151245,
513
+ "learning_rate": 4.934002070946206e-05,
514
+ "loss": 1.8497,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.6608187134502925,
519
+ "grad_norm": 3.90553879737854,
520
+ "learning_rate": 4.802052207868654e-05,
521
+ "loss": 1.692,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.6842105263157894,
526
+ "grad_norm": 5.151843070983887,
527
+ "learning_rate": 4.670240297826523e-05,
528
+ "loss": 1.7849,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.7076023391812867,
533
+ "grad_norm": 4.96315336227417,
534
+ "learning_rate": 4.5386582026834906e-05,
535
+ "loss": 1.9887,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.7309941520467835,
540
+ "grad_norm": 1.8645200729370117,
541
+ "learning_rate": 4.407397624141487e-05,
542
+ "loss": 2.2243,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.7543859649122808,
547
+ "grad_norm": 2.2499165534973145,
548
+ "learning_rate": 4.276550039832299e-05,
549
+ "loss": 2.24,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.7777777777777777,
554
+ "grad_norm": 2.531435251235962,
555
+ "learning_rate": 4.146206639565312e-05,
556
+ "loss": 2.167,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.801169590643275,
561
+ "grad_norm": 2.621704578399658,
562
+ "learning_rate": 4.01645826177586e-05,
563
+ "loss": 2.0048,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.8245614035087718,
568
+ "grad_norm": 3.041447401046753,
569
+ "learning_rate": 3.887395330218429e-05,
570
+ "loss": 1.9858,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.8479532163742691,
575
+ "grad_norm": 3.520282745361328,
576
+ "learning_rate": 3.759107790948882e-05,
577
+ "loss": 1.9349,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.871345029239766,
582
+ "grad_norm": 3.5151638984680176,
583
+ "learning_rate": 3.631685049639586e-05,
584
+ "loss": 1.6562,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.8947368421052633,
589
+ "grad_norm": 4.325654983520508,
590
+ "learning_rate": 3.505215909271149e-05,
591
+ "loss": 1.9125,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.9181286549707601,
596
+ "grad_norm": 5.122260570526123,
597
+ "learning_rate": 3.379788508244171e-05,
598
+ "loss": 1.6561,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.9415204678362574,
603
+ "grad_norm": 5.443163871765137,
604
+ "learning_rate": 3.255490258954167e-05,
605
+ "loss": 2.5903,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.9649122807017543,
610
+ "grad_norm": 2.3221733570098877,
611
+ "learning_rate": 3.132407786872442e-05,
612
+ "loss": 1.9197,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.9883040935672516,
617
+ "grad_norm": 4.910060405731201,
618
+ "learning_rate": 3.0106268701753965e-05,
619
+ "loss": 2.2014,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 2.0116959064327484,
624
+ "grad_norm": 3.926137685775757,
625
+ "learning_rate": 2.8902323799643116e-05,
626
+ "loss": 2.227,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 2.0350877192982457,
631
+ "grad_norm": 1.8208245038986206,
632
+ "learning_rate": 2.771308221117309e-05,
633
+ "loss": 1.8213,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 2.0584795321637426,
638
+ "grad_norm": 2.0533692836761475,
639
+ "learning_rate": 2.6539372738146695e-05,
640
+ "loss": 1.6875,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 2.08187134502924,
645
+ "grad_norm": 2.5335185527801514,
646
+ "learning_rate": 2.5382013357782893e-05,
647
+ "loss": 1.7146,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 2.1052631578947367,
652
+ "grad_norm": 2.658461093902588,
653
+ "learning_rate": 2.4241810652655196e-05,
654
+ "loss": 1.6028,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 2.128654970760234,
659
+ "grad_norm": 2.784259796142578,
660
+ "learning_rate": 2.3119559248571128e-05,
661
+ "loss": 1.5149,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 2.152046783625731,
666
+ "grad_norm": 3.2446987628936768,
667
+ "learning_rate": 2.2016041260784605e-05,
668
+ "loss": 1.2587,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 2.175438596491228,
673
+ "grad_norm": 3.726407527923584,
674
+ "learning_rate": 2.0932025748927013e-05,
675
+ "loss": 1.286,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 2.198830409356725,
680
+ "grad_norm": 4.698680400848389,
681
+ "learning_rate": 1.9868268181037185e-05,
682
+ "loss": 1.2943,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 2.2222222222222223,
687
+ "grad_norm": 4.862926483154297,
688
+ "learning_rate": 1.8825509907063327e-05,
689
+ "loss": 0.9368,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 2.245614035087719,
694
+ "grad_norm": 4.17417573928833,
695
+ "learning_rate": 1.7804477642204222e-05,
696
+ "loss": 1.8199,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 2.2690058479532165,
701
+ "grad_norm": 3.123291254043579,
702
+ "learning_rate": 1.6805882960449594e-05,
703
+ "loss": 2.1358,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 2.2923976608187133,
708
+ "grad_norm": 3.0750467777252197,
709
+ "learning_rate": 1.5830421798672568e-05,
710
+ "loss": 1.6731,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 2.3157894736842106,
715
+ "grad_norm": 3.460376262664795,
716
+ "learning_rate": 1.4878773971620074e-05,
717
+ "loss": 1.7389,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 2.3391812865497075,
722
+ "grad_norm": 3.5447030067443848,
723
+ "learning_rate": 1.3951602698138771e-05,
724
+ "loss": 1.5398,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 2.3391812865497075,
729
+ "eval_loss": 2.5794575214385986,
730
+ "eval_runtime": 3.2727,
731
+ "eval_samples_per_second": 22.0,
732
+ "eval_steps_per_second": 5.5,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.174757862624461e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null