prxy5605 commited on
Commit
5b00781
·
verified ·
1 Parent(s): 0f16e40

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 sha256:18e1a297144d32248f1c7dc07c1813303a2da583dec25b0859f70479414ac563
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f23bed06c6f6698a348dae656bfb0f246ea6372bedfd2b88fa399c55d57763
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf37cb24900e85bdc08ff54c7a4afd909b649684159eb6fffdbff9beb5e27759
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1050a5f3e8018cade3153e4eddcec43445e55d1d7fffe0d6d8b43abddb7a3d6
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b9a631606a4a898ed3927176e0e09be3a78fda22b1dd02f6556ee79c71148f8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd0608c3e3453c73fdb85c1c65549e4205179ce3d24363aba902e2935b7222f
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": 0.9113385081291199,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.022799817601459188,
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": 10.563,
374
  "eval_steps_per_second": 2.642,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.190764995162931e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8197675347328186,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.045599635202918376,
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": 10.563,
374
  "eval_steps_per_second": 2.642,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.023255813953488372,
379
+ "grad_norm": 16.446622848510742,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 3.0671,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.023711810305517556,
386
+ "grad_norm": 10.394733428955078,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 3.1367,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.02416780665754674,
393
+ "grad_norm": 11.116695404052734,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.7149,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.024623803009575923,
400
+ "grad_norm": 9.479421615600586,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.1254,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.025079799361605107,
407
+ "grad_norm": 11.42734146118164,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.393,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.02553579571363429,
414
+ "grad_norm": 9.619385719299316,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.6756,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.025991792065663474,
421
+ "grad_norm": 10.887063980102539,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 3.0928,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.026447788417692658,
428
+ "grad_norm": 9.697304725646973,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.6691,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.026903784769721842,
435
+ "grad_norm": 10.840964317321777,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.8811,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.027359781121751026,
442
+ "grad_norm": 12.989250183105469,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 3.8215,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.02781577747378021,
449
+ "grad_norm": 12.489930152893066,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 3.967,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.028271773825809393,
456
+ "grad_norm": 11.065751075744629,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.8307,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.028727770177838577,
463
+ "grad_norm": 10.985672950744629,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 3.1239,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.02918376652986776,
470
+ "grad_norm": 9.590174674987793,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.7839,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.029639762881896944,
477
+ "grad_norm": 12.237695693969727,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 3.5155,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.030095759233926128,
484
+ "grad_norm": 15.1380033493042,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 3.4588,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.030551755585955312,
491
+ "grad_norm": 162.89707946777344,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 3.0448,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.031007751937984496,
498
+ "grad_norm": 13.830486297607422,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 3.0779,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.03146374829001368,
505
+ "grad_norm": 11.294425010681152,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.9532,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.03191974464204286,
512
+ "grad_norm": 10.481371879577637,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 3.4687,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.03237574099407205,
519
+ "grad_norm": 12.793365478515625,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 3.5947,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.03283173734610123,
526
+ "grad_norm": 12.153921127319336,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 3.8798,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.033287733698130414,
533
+ "grad_norm": 9.509449005126953,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.9595,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.0337437300501596,
540
+ "grad_norm": 10.440327644348145,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 3.7834,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.03419972640218878,
547
+ "grad_norm": 10.908466339111328,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.6557,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.034655722754217966,
554
+ "grad_norm": 9.98528003692627,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.4296,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.03511171910624715,
561
+ "grad_norm": 15.787983894348145,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 4.7181,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.03556771545827633,
568
+ "grad_norm": 12.403399467468262,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 3.1346,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.03602371181030552,
575
+ "grad_norm": 12.2731351852417,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.8631,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.0364797081623347,
582
+ "grad_norm": 14.62734317779541,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 3.9177,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.036935704514363885,
589
+ "grad_norm": 12.990211486816406,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 3.5621,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.03739170086639307,
596
+ "grad_norm": 14.018969535827637,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 3.4686,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.03784769721842225,
603
+ "grad_norm": 14.162925720214844,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 3.3132,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.038303693570451436,
610
+ "grad_norm": 14.519307136535645,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 4.188,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.03875968992248062,
617
+ "grad_norm": 12.667447090148926,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 3.8917,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0392156862745098,
624
+ "grad_norm": 12.733670234680176,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 3.1904,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.03967168262653899,
631
+ "grad_norm": 11.787132263183594,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 3.0343,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.04012767897856817,
638
+ "grad_norm": 10.446242332458496,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 3.3589,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.040583675330597355,
645
+ "grad_norm": 12.251482009887695,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 3.7822,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.04103967168262654,
652
+ "grad_norm": 13.403604507446289,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 3.5298,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.04149566803465572,
659
+ "grad_norm": 9.842473030090332,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.8747,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.041951664386684906,
666
+ "grad_norm": 12.207097053527832,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.7642,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.04240766073871409,
673
+ "grad_norm": 11.435685157775879,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 3.9007,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.04286365709074327,
680
+ "grad_norm": 10.784540176391602,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 3.7834,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.04331965344277246,
687
+ "grad_norm": 12.038006782531738,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 3.9517,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.04377564979480164,
694
+ "grad_norm": 11.988702774047852,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 3.4095,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.044231646146830825,
701
+ "grad_norm": 10.996843338012695,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.1867,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.04468764249886001,
708
+ "grad_norm": 14.686224937438965,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 4.0562,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.04514363885088919,
715
+ "grad_norm": 14.393037796020508,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 4.388,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.045599635202918376,
722
+ "grad_norm": 17.71428871154785,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 4.8689,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.045599635202918376,
729
+ "eval_loss": 0.8197675347328186,
730
+ "eval_runtime": 349.5978,
731
+ "eval_samples_per_second": 10.566,
732
+ "eval_steps_per_second": 2.643,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.4345755040101171e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null