prxy5606 commited on
Commit
6975c25
·
verified ·
1 Parent(s): 7e6abd4

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:fe44c0c4a1dc511022fe2af1b615e63e9bc4870b0a35d0e747c0d3b5018dc489
3
  size 54285928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4772adf351f1ce35f37f56782a164c44a3fc1fc46ab46bbd8010c53b3e50bf39
3
  size 54285928
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86cc54f81f14fa1b56e6ef8b76d135dde39c648387b2ed485412251aa9490928
3
  size 108668858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a74f6e948d670aef9e3fd660dc4c84219a3f18341d2c44af76e80058b8e941f
3
  size 108668858
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a26e9e0ae61ca05e193bb601889410a51af9791f2ee0ef08ddefe14a8decc43
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7255bd9a0cfa637aa42f1603654591ddd1e84bc45db67f8fc7aa322352d44ac7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ece3236edcb393fe9fe067fb4c27aaaf2d1a125595517cb84b2456d9b62475c0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.247523784637451,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.1718213058419244,
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": 86.468,
374
  "eval_steps_per_second": 43.234,
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": 1614908479242240.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.0897529125213623,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.3436426116838488,
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": 86.468,
374
  "eval_steps_per_second": 43.234,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.17525773195876287,
379
+ "grad_norm": 2.528313159942627,
380
+ "learning_rate": 7.938926261462366e-05,
381
+ "loss": 2.3671,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.17869415807560138,
386
+ "grad_norm": 2.315145969390869,
387
+ "learning_rate": 7.754484907260513e-05,
388
+ "loss": 2.3046,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.18213058419243985,
393
+ "grad_norm": 1.7192437648773193,
394
+ "learning_rate": 7.564496387029532e-05,
395
+ "loss": 2.1694,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.18556701030927836,
400
+ "grad_norm": 1.133732557296753,
401
+ "learning_rate": 7.369343312364993e-05,
402
+ "loss": 2.1953,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.18900343642611683,
407
+ "grad_norm": 0.713290274143219,
408
+ "learning_rate": 7.169418695587791e-05,
409
+ "loss": 2.053,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.19243986254295534,
414
+ "grad_norm": 0.5978623032569885,
415
+ "learning_rate": 6.965125158269619e-05,
416
+ "loss": 2.12,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.1958762886597938,
421
+ "grad_norm": 0.5948276519775391,
422
+ "learning_rate": 6.756874120406714e-05,
423
+ "loss": 2.1898,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.19931271477663232,
428
+ "grad_norm": 0.6025165319442749,
429
+ "learning_rate": 6.545084971874738e-05,
430
+ "loss": 2.1185,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.2027491408934708,
435
+ "grad_norm": 0.5380327105522156,
436
+ "learning_rate": 6.330184227833376e-05,
437
+ "loss": 2.0913,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.20618556701030927,
442
+ "grad_norm": 0.5481085777282715,
443
+ "learning_rate": 6.112604669781572e-05,
444
+ "loss": 1.9754,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.20962199312714777,
449
+ "grad_norm": 0.5363459587097168,
450
+ "learning_rate": 5.8927844739931834e-05,
451
+ "loss": 2.1673,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.21305841924398625,
456
+ "grad_norm": 0.4893956482410431,
457
+ "learning_rate": 5.6711663290882776e-05,
458
+ "loss": 2.0366,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.21649484536082475,
463
+ "grad_norm": 0.4866885542869568,
464
+ "learning_rate": 5.448196544517168e-05,
465
+ "loss": 2.0198,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.21993127147766323,
470
+ "grad_norm": 0.4834136664867401,
471
+ "learning_rate": 5.2243241517525754e-05,
472
+ "loss": 2.058,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.22336769759450173,
477
+ "grad_norm": 0.47863930463790894,
478
+ "learning_rate": 5e-05,
479
+ "loss": 2.0112,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.2268041237113402,
484
+ "grad_norm": 0.5112380385398865,
485
+ "learning_rate": 4.775675848247427e-05,
486
+ "loss": 2.0965,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.23024054982817868,
491
+ "grad_norm": 0.4476987421512604,
492
+ "learning_rate": 4.551803455482833e-05,
493
+ "loss": 2.013,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.23367697594501718,
498
+ "grad_norm": 0.4423470199108124,
499
+ "learning_rate": 4.328833670911724e-05,
500
+ "loss": 1.9623,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.23711340206185566,
505
+ "grad_norm": 0.4461471140384674,
506
+ "learning_rate": 4.107215526006817e-05,
507
+ "loss": 2.0052,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.24054982817869416,
512
+ "grad_norm": 0.5078745484352112,
513
+ "learning_rate": 3.887395330218429e-05,
514
+ "loss": 2.0747,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.24398625429553264,
519
+ "grad_norm": 0.4781670868396759,
520
+ "learning_rate": 3.6698157721666246e-05,
521
+ "loss": 2.125,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.24742268041237114,
526
+ "grad_norm": 0.47303977608680725,
527
+ "learning_rate": 3.4549150281252636e-05,
528
+ "loss": 1.9952,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2508591065292096,
533
+ "grad_norm": 0.4364500343799591,
534
+ "learning_rate": 3.243125879593286e-05,
535
+ "loss": 2.0303,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.2542955326460481,
540
+ "grad_norm": 0.47456878423690796,
541
+ "learning_rate": 3.0348748417303823e-05,
542
+ "loss": 2.1002,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.25773195876288657,
547
+ "grad_norm": 0.4605971872806549,
548
+ "learning_rate": 2.8305813044122097e-05,
549
+ "loss": 2.0942,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2611683848797251,
554
+ "grad_norm": 0.4621974229812622,
555
+ "learning_rate": 2.630656687635007e-05,
556
+ "loss": 2.0768,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.2646048109965636,
561
+ "grad_norm": 0.4659442603588104,
562
+ "learning_rate": 2.43550361297047e-05,
563
+ "loss": 2.0493,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.26804123711340205,
568
+ "grad_norm": 0.47574934363365173,
569
+ "learning_rate": 2.245515092739488e-05,
570
+ "loss": 2.0854,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.27147766323024053,
575
+ "grad_norm": 0.46890461444854736,
576
+ "learning_rate": 2.061073738537635e-05,
577
+ "loss": 2.0456,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.27491408934707906,
582
+ "grad_norm": 0.4491337239742279,
583
+ "learning_rate": 1.8825509907063327e-05,
584
+ "loss": 2.0834,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.27835051546391754,
589
+ "grad_norm": 0.46741199493408203,
590
+ "learning_rate": 1.7103063703014372e-05,
591
+ "loss": 2.0842,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.281786941580756,
596
+ "grad_norm": 0.47655144333839417,
597
+ "learning_rate": 1.544686755065677e-05,
598
+ "loss": 2.1256,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.2852233676975945,
603
+ "grad_norm": 0.45900094509124756,
604
+ "learning_rate": 1.3860256808630428e-05,
605
+ "loss": 2.1237,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.28865979381443296,
610
+ "grad_norm": 0.4810255169868469,
611
+ "learning_rate": 1.2346426699819458e-05,
612
+ "loss": 2.1193,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2920962199312715,
617
+ "grad_norm": 0.4391408860683441,
618
+ "learning_rate": 1.090842587659851e-05,
619
+ "loss": 2.0282,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.29553264604810997,
624
+ "grad_norm": 0.4718332886695862,
625
+ "learning_rate": 9.549150281252633e-06,
626
+ "loss": 2.1053,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.29896907216494845,
631
+ "grad_norm": 0.48831039667129517,
632
+ "learning_rate": 8.271337313934869e-06,
633
+ "loss": 2.0954,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.3024054982817869,
638
+ "grad_norm": 0.4913262128829956,
639
+ "learning_rate": 7.077560319906695e-06,
640
+ "loss": 1.9763,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.30584192439862545,
645
+ "grad_norm": 0.5028262734413147,
646
+ "learning_rate": 5.9702234071631e-06,
647
+ "loss": 2.1451,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.30927835051546393,
652
+ "grad_norm": 0.5151122808456421,
653
+ "learning_rate": 4.951556604879048e-06,
654
+ "loss": 2.1428,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.3127147766323024,
659
+ "grad_norm": 0.5513173937797546,
660
+ "learning_rate": 4.023611372427471e-06,
661
+ "loss": 2.1041,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.3161512027491409,
666
+ "grad_norm": 0.541987955570221,
667
+ "learning_rate": 3.18825646801314e-06,
668
+ "loss": 2.2697,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.31958762886597936,
673
+ "grad_norm": 0.638981282711029,
674
+ "learning_rate": 2.4471741852423237e-06,
675
+ "loss": 2.2158,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.3230240549828179,
680
+ "grad_norm": 0.6572893261909485,
681
+ "learning_rate": 1.8018569652073381e-06,
682
+ "loss": 2.1798,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.32646048109965636,
687
+ "grad_norm": 0.6969611644744873,
688
+ "learning_rate": 1.2536043909088191e-06,
689
+ "loss": 2.2424,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.32989690721649484,
694
+ "grad_norm": 0.7528119087219238,
695
+ "learning_rate": 8.035205700685167e-07,
696
+ "loss": 2.1574,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.3333333333333333,
701
+ "grad_norm": 0.8161905407905579,
702
+ "learning_rate": 4.52511911603265e-07,
703
+ "loss": 2.3423,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.33676975945017185,
708
+ "grad_norm": 0.9732829928398132,
709
+ "learning_rate": 2.012853002380466e-07,
710
+ "loss": 2.164,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.3402061855670103,
715
+ "grad_norm": 1.047484278678894,
716
+ "learning_rate": 5.0346672934270534e-08,
717
+ "loss": 2.2618,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.3436426116838488,
722
+ "grad_norm": 1.2029303312301636,
723
+ "learning_rate": 0.0,
724
+ "loss": 2.36,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.3436426116838488,
729
+ "eval_loss": 2.0897529125213623,
730
+ "eval_runtime": 5.6482,
731
+ "eval_samples_per_second": 86.753,
732
+ "eval_steps_per_second": 43.376,
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": 3200049060249600.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null