prxy5607 commited on
Commit
03d0740
·
verified ·
1 Parent(s): dab69a0

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:cc8329b833df263ade07655e447618245b3e5d4cc3eda1d0591aa135d25d0894
3
  size 72936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f3a2fd180656a2321e1ad89d3037ea82639d6bc086312cbab1f9eea6fab2f6
3
  size 72936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:730b07eaadcb31489cd9e5b68a8040902b91a3e736524200cc22dd39fe92418b
3
  size 151106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138a8e60335004b7ebbb59a08d2c692dfe2b2f922b57506d9174400ca40200fa
3
  size 151106
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58ad5c339ca89f9230479249d71a6025f6a2173e7bde89a2290f94338039460a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d883b5711f7820f8c0e95d92e1def4a77df7b9d9c954cdd897d2967dfc6fc9b
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": 12.453710556030273,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.047573739295908656,
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": 113.812,
374
  "eval_steps_per_second": 28.485,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 221758095360.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 12.433951377868652,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.09514747859181731,
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": 113.812,
374
  "eval_steps_per_second": 28.485,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.048525214081826834,
379
+ "grad_norm": 0.04241883382201195,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 12.453,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.049476688867745006,
386
+ "grad_norm": 0.040811438113451004,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 12.4532,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.05042816365366318,
393
+ "grad_norm": 0.04538936913013458,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 12.4549,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.05137963843958135,
400
+ "grad_norm": 0.04279905930161476,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 12.4553,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.05233111322549953,
407
+ "grad_norm": 0.04463065788149834,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 12.4545,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0532825880114177,
414
+ "grad_norm": 0.045460935682058334,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 12.4536,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.05423406279733587,
421
+ "grad_norm": 0.04949776828289032,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 12.453,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.05518553758325404,
428
+ "grad_norm": 0.048668451607227325,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 12.4534,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.056137012369172214,
435
+ "grad_norm": 0.05029277876019478,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 12.4509,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.05708848715509039,
442
+ "grad_norm": 0.04988345131278038,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 12.4542,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.058039961941008564,
449
+ "grad_norm": 0.057984285056591034,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 12.4528,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.058991436726926735,
456
+ "grad_norm": 0.055844224989414215,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 12.4509,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.05994291151284491,
463
+ "grad_norm": 0.05761745199561119,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 12.4493,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.060894386298763085,
470
+ "grad_norm": 0.056190405040979385,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 12.4529,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.06184586108468126,
477
+ "grad_norm": 0.06360480189323425,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 12.4507,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.06279733587059944,
484
+ "grad_norm": 0.06286083161830902,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 12.4494,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.06374881065651761,
491
+ "grad_norm": 0.06642145663499832,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 12.4516,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.06470028544243578,
498
+ "grad_norm": 0.06627269089221954,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 12.4492,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.06565176022835395,
505
+ "grad_norm": 0.07501520216464996,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 12.4477,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.06660323501427212,
512
+ "grad_norm": 0.07477276027202606,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 12.4466,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.0675547098001903,
519
+ "grad_norm": 0.0773748978972435,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 12.4473,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.06850618458610847,
526
+ "grad_norm": 0.0730040967464447,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 12.4467,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.06945765937202664,
533
+ "grad_norm": 0.07389922440052032,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 12.4449,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.07040913415794481,
540
+ "grad_norm": 0.08344914764165878,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 12.4473,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.071360608943863,
547
+ "grad_norm": 0.08166919648647308,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 12.4463,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.07231208372978117,
554
+ "grad_norm": 0.07941465824842453,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 12.4457,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.07326355851569934,
561
+ "grad_norm": 0.08082740008831024,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 12.4444,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.07421503330161751,
568
+ "grad_norm": 0.08413875848054886,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 12.4461,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.07516650808753568,
575
+ "grad_norm": 0.09172741323709488,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 12.4452,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.07611798287345385,
582
+ "grad_norm": 0.09037219732999802,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 12.4443,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.07706945765937202,
589
+ "grad_norm": 0.09228965640068054,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 12.4366,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.0780209324452902,
596
+ "grad_norm": 0.08169149607419968,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 12.4429,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.07897240723120837,
603
+ "grad_norm": 0.09187179803848267,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 12.4403,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.07992388201712655,
610
+ "grad_norm": 0.09605192393064499,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 12.44,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.08087535680304472,
617
+ "grad_norm": 0.1012379601597786,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 12.4397,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.0818268315889629,
624
+ "grad_norm": 0.09477464854717255,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 12.4398,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.08277830637488107,
631
+ "grad_norm": 0.09537472575902939,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 12.4408,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.08372978116079924,
638
+ "grad_norm": 0.09693397581577301,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 12.4391,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.08468125594671741,
645
+ "grad_norm": 0.09416460990905762,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 12.4377,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.08563273073263558,
652
+ "grad_norm": 0.09926611185073853,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 12.4386,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.08658420551855375,
659
+ "grad_norm": 0.09036323428153992,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 12.439,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.08753568030447194,
666
+ "grad_norm": 0.09396945685148239,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 12.436,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.08848715509039011,
673
+ "grad_norm": 0.10250120609998703,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 12.4326,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.08943862987630828,
680
+ "grad_norm": 0.09737430512905121,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 12.4376,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.09039010466222645,
687
+ "grad_norm": 0.098517045378685,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 12.4316,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.09134157944814462,
694
+ "grad_norm": 0.09766911715269089,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 12.4382,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0922930542340628,
701
+ "grad_norm": 0.10806909203529358,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 12.4331,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.09324452901998097,
708
+ "grad_norm": 0.08718223124742508,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 12.4352,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.09419600380589914,
715
+ "grad_norm": 0.09523314237594604,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 12.4348,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.09514747859181731,
722
+ "grad_norm": 0.09032314270734787,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 12.4365,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.09514747859181731,
729
+ "eval_loss": 12.433951377868652,
730
+ "eval_runtime": 15.6067,
731
+ "eval_samples_per_second": 113.413,
732
+ "eval_steps_per_second": 28.385,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 443516190720.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null