aleegis10 commited on
Commit
a70682a
·
verified ·
1 Parent(s): 5d67841

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:a3490293c6c01cebe0e630aa9ed00b0dde9cb8c4b39617eb33c0db8f9f00c477
3
  size 332316480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa65785c872622d0758aeb260f7e6dd961ab61c2da8fbd56aafedfe1ec2ded76
3
  size 332316480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b01f54029f1bc2f30b987cae3fa61900cc38c82c2d9d6b14790fca294b897a18
3
  size 169157892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15cc5595b92450a8f5bce95694179fd6420c2e057c827bbe22b2fb91ef7054db
3
  size 169157892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43a01678b1e299f075224f8b2b58dd952e473f1c6c0cb1b371c51bb3f07752ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b4a3ec22b1ca46f595d70f8cfa19f5fea9b0669aaf8707b2be6f4011961909
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": 2.2572968006134033,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.20408163265306123,
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": 22.433,
374
  "eval_steps_per_second": 5.649,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.07184013033472e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.0559909343719482,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.40816326530612246,
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": 22.433,
374
  "eval_steps_per_second": 5.649,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.20816326530612245,
379
+ "grad_norm": 4.218966484069824,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.227,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.21224489795918366,
386
+ "grad_norm": 3.6228156089782715,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.1094,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2163265306122449,
393
+ "grad_norm": 2.5655953884124756,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.8853,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.22040816326530613,
400
+ "grad_norm": 1.9767965078353882,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.7629,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.22448979591836735,
407
+ "grad_norm": 2.2300515174865723,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.8235,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.22857142857142856,
414
+ "grad_norm": 2.356839656829834,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.7778,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.23265306122448978,
421
+ "grad_norm": 2.4376683235168457,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.796,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.23673469387755103,
428
+ "grad_norm": 2.6358144283294678,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.0317,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.24081632653061225,
435
+ "grad_norm": 2.4748549461364746,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.1629,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.24489795918367346,
442
+ "grad_norm": 2.625441789627075,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.9798,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.24897959183673468,
449
+ "grad_norm": 2.1958751678466797,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.8895,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2530612244897959,
456
+ "grad_norm": 2.5427582263946533,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.0609,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2571428571428571,
463
+ "grad_norm": 2.3777239322662354,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.9472,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2612244897959184,
470
+ "grad_norm": 2.361562967300415,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.984,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.2653061224489796,
477
+ "grad_norm": 2.377790689468384,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.912,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.2693877551020408,
484
+ "grad_norm": 2.3698973655700684,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.0221,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.27346938775510204,
491
+ "grad_norm": 2.270094871520996,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.8288,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.27755102040816326,
498
+ "grad_norm": 2.254058599472046,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.981,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.2816326530612245,
505
+ "grad_norm": 2.5751991271972656,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.107,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.2857142857142857,
512
+ "grad_norm": 3.247217893600464,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.8935,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.2897959183673469,
519
+ "grad_norm": 2.267015218734741,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.8044,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.2938775510204082,
526
+ "grad_norm": 2.542069435119629,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.9103,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2979591836734694,
533
+ "grad_norm": 2.367809295654297,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.9915,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3020408163265306,
540
+ "grad_norm": 2.3319528102874756,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.9277,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.30612244897959184,
547
+ "grad_norm": 2.4607839584350586,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.9147,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.31020408163265306,
554
+ "grad_norm": 2.590803861618042,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.1734,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3142857142857143,
561
+ "grad_norm": 2.5294189453125,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.8926,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3183673469387755,
568
+ "grad_norm": 3.961461305618286,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.8666,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3224489795918367,
575
+ "grad_norm": 2.4877421855926514,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.021,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.32653061224489793,
582
+ "grad_norm": 2.5108823776245117,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.0798,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.3306122448979592,
589
+ "grad_norm": 2.6391265392303467,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.0319,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.3346938775510204,
596
+ "grad_norm": 2.3597116470336914,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.9081,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.33877551020408164,
603
+ "grad_norm": 2.3042685985565186,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.7745,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.34285714285714286,
610
+ "grad_norm": 2.576266288757324,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.007,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.3469387755102041,
617
+ "grad_norm": 2.5641062259674072,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.969,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.3510204081632653,
624
+ "grad_norm": 2.6728813648223877,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.0079,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3551020408163265,
631
+ "grad_norm": 2.360001802444458,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.9353,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.35918367346938773,
638
+ "grad_norm": 2.9285295009613037,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.9953,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.363265306122449,
645
+ "grad_norm": 2.799461603164673,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.0193,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.3673469387755102,
652
+ "grad_norm": 2.408754348754883,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.9315,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.37142857142857144,
659
+ "grad_norm": 6.137120723724365,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.0991,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.37551020408163266,
666
+ "grad_norm": 3.0358972549438477,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.154,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.3795918367346939,
673
+ "grad_norm": 2.8257830142974854,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.0584,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3836734693877551,
680
+ "grad_norm": 2.6828041076660156,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.9637,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.3877551020408163,
687
+ "grad_norm": 2.435418128967285,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.7421,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.39183673469387753,
694
+ "grad_norm": 2.78086519241333,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.9335,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.39591836734693875,
701
+ "grad_norm": 2.709322929382324,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.0148,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.4,
708
+ "grad_norm": 2.8029189109802246,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.0737,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.40408163265306124,
715
+ "grad_norm": 3.100375175476074,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.1987,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.40816326530612246,
722
+ "grad_norm": 3.068387269973755,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.0296,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.40816326530612246,
729
+ "eval_loss": 2.0559909343719482,
730
+ "eval_runtime": 18.4037,
731
+ "eval_samples_per_second": 22.441,
732
+ "eval_steps_per_second": 5.651,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 4.14368026066944e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null