arcwarden46 commited on
Commit
8301ab4
·
verified ·
1 Parent(s): f3bedca

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 sha256:02f50327f24c8ee32bf94b9aa2e55aabd22d829e5ca94a84f4b195317a246c57
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b9d6e2a783a0fda536017f61c0ad1922fe44b1c8779fbc2b954d03226b6921
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:672c8c4471052feca2feb25aaa96d87c5c5af101766a9175d30e356dca67f2f5
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:face4b94a1ca90b0023da6688e996564874d84dc853878dd1892d6d02e349a1f
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5c444494cc1966e8c38914400d06b2c503ea868e16c9068f49953e70f65f014
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed1e62e379e5c95a4ce14fb770553a251c19d0b44309e01a2a59b1f71883aac6
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": 1.7835716009140015,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.29027576197387517,
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": 11.732,
374
  "eval_steps_per_second": 2.953,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 5.73309481648128e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7677788734436035,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.5805515239477503,
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": 11.732,
374
  "eval_steps_per_second": 2.953,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.2960812772133527,
379
+ "grad_norm": 0.40847522020339966,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.8509,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.3018867924528302,
386
+ "grad_norm": 0.41111356019973755,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.8034,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.3076923076923077,
393
+ "grad_norm": 0.39087432622909546,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.8401,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3134978229317852,
400
+ "grad_norm": 0.39595600962638855,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.8924,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.3193033381712627,
407
+ "grad_norm": 0.4029504060745239,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.7423,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.3251088534107402,
414
+ "grad_norm": 0.3971380591392517,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.8423,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.3309143686502177,
421
+ "grad_norm": 0.4342693090438843,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.7788,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.3367198838896952,
428
+ "grad_norm": 0.38115909695625305,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.8777,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.34252539912917274,
435
+ "grad_norm": 0.526332676410675,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.8461,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3483309143686502,
442
+ "grad_norm": 0.45587947964668274,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.6886,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.35413642960812775,
449
+ "grad_norm": 0.40341612696647644,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.8618,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.3599419448476052,
456
+ "grad_norm": 0.5133787393569946,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.6871,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.36574746008708275,
463
+ "grad_norm": 0.45418137311935425,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.7365,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.37155297532656023,
470
+ "grad_norm": 0.4577997028827667,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.7544,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.37735849056603776,
477
+ "grad_norm": 0.44454094767570496,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.7263,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.38316400580551524,
484
+ "grad_norm": 0.43912273645401,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.7176,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3889695210449927,
491
+ "grad_norm": 0.4508310854434967,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.8291,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.39477503628447025,
498
+ "grad_norm": 0.46372470259666443,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.7316,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.4005805515239477,
505
+ "grad_norm": 0.4595024585723877,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.7626,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.40638606676342526,
512
+ "grad_norm": 0.47752857208251953,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.7949,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.41219158200290273,
519
+ "grad_norm": 0.4701814353466034,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.884,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.41799709724238027,
526
+ "grad_norm": 0.49096331000328064,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.8549,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.42380261248185774,
533
+ "grad_norm": 0.5183019638061523,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.7396,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.4296081277213353,
540
+ "grad_norm": 0.6562801599502563,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.8548,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.43541364296081275,
547
+ "grad_norm": 0.5333163142204285,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.7933,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.4412191582002903,
554
+ "grad_norm": 0.5598500370979309,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.764,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.44702467343976776,
561
+ "grad_norm": 0.616254985332489,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.8519,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.4528301886792453,
568
+ "grad_norm": 0.5128965973854065,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.6843,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.45863570391872277,
575
+ "grad_norm": 0.5723729133605957,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.8211,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.4644412191582003,
582
+ "grad_norm": 0.5582553148269653,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.7159,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.4702467343976778,
589
+ "grad_norm": 0.6017863750457764,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.8328,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.4760522496371553,
596
+ "grad_norm": 0.646784245967865,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.7488,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.4818577648766328,
603
+ "grad_norm": 0.621480405330658,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.7754,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.4876632801161103,
610
+ "grad_norm": 0.7075855731964111,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.6894,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.4934687953555878,
617
+ "grad_norm": 0.8735288977622986,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.5269,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.49927431059506533,
624
+ "grad_norm": 2.9787540435791016,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.7141,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.5050798258345428,
631
+ "grad_norm": 0.8107753992080688,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.018,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.5108853410740203,
638
+ "grad_norm": 0.42176181077957153,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.9651,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.5166908563134979,
645
+ "grad_norm": 0.4151810109615326,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.789,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.5224963715529753,
652
+ "grad_norm": 0.386679470539093,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.8299,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.5283018867924528,
659
+ "grad_norm": 0.4106220602989197,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.8651,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.5341074020319303,
666
+ "grad_norm": 0.39643245935440063,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.9113,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.5399129172714079,
673
+ "grad_norm": 0.3862471580505371,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.8414,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.5457184325108854,
680
+ "grad_norm": 0.3962131142616272,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.9122,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.5515239477503628,
687
+ "grad_norm": 0.4000537395477295,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.723,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.5573294629898403,
694
+ "grad_norm": 0.38008323311805725,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.8512,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.5631349782293179,
701
+ "grad_norm": 0.38584694266319275,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.8828,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.5689404934687954,
708
+ "grad_norm": 0.38245323300361633,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.6953,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.5747460087082729,
715
+ "grad_norm": 0.4093793034553528,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.8376,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.5805515239477503,
722
+ "grad_norm": 0.38503092527389526,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.8735,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.5805515239477503,
729
+ "eval_loss": 1.7677788734436035,
730
+ "eval_runtime": 24.699,
731
+ "eval_samples_per_second": 11.741,
732
+ "eval_steps_per_second": 2.956,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.1451856895921357e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null