prxy5607 commited on
Commit
7c3d16c
·
verified ·
1 Parent(s): 3b56784

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:a9ee1a94a9f670c537f8d05c3195ab7cf06b71d01af63f2676222568b20c145d
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d1fd0c9285332e268bd1b8bdc8ce4bb0963dbab23a627f0743ec386f2b05483
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e4cc97a9897c9a7da7d92cb2437bbc50f0da9fb46be9640e474649d472e857c
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f1183fdfd2552d39093b6ef8d9de41cbc8a3f2edc7b02a486c58f6822bc09f2
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87721e33200438be29c7f03d550b8c7e17d801416fde909bbe2fcffaa1f66049
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d215111a211bb199cd2db6aa686a73f2b08f35d3e54420f59ebc68cc75498062
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": 4.55251932144165,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.2557544757033248,
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": 14.023,
374
  "eval_steps_per_second": 3.527,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.71020323176448e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.1948964595794678,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.5115089514066496,
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": 14.023,
374
  "eval_steps_per_second": 3.527,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.2608695652173913,
379
+ "grad_norm": 33.81939697265625,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 6.0675,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.2659846547314578,
386
+ "grad_norm": 8.315890312194824,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 4.3208,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2710997442455243,
393
+ "grad_norm": 6.041251182556152,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 4.0021,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.27621483375959077,
400
+ "grad_norm": 5.480395793914795,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 3.5547,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.2813299232736573,
407
+ "grad_norm": 4.745906352996826,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 3.1183,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.2864450127877238,
414
+ "grad_norm": 4.063253402709961,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.7754,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2915601023017903,
421
+ "grad_norm": 2.9666452407836914,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.6057,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2966751918158568,
428
+ "grad_norm": 2.41210675239563,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.9152,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.30179028132992325,
435
+ "grad_norm": 2.5263257026672363,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.5977,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.3069053708439898,
442
+ "grad_norm": 2.23828125,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.6563,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.31202046035805625,
449
+ "grad_norm": 2.502732276916504,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.5823,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.3171355498721228,
456
+ "grad_norm": 2.560762882232666,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.6343,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.32225063938618925,
463
+ "grad_norm": 2.3925020694732666,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.7233,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.3273657289002558,
470
+ "grad_norm": 2.2098705768585205,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.2702,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.33248081841432225,
477
+ "grad_norm": 2.209908962249756,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.1663,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3375959079283887,
484
+ "grad_norm": 2.2588908672332764,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.2931,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.34271099744245526,
491
+ "grad_norm": 2.3859808444976807,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.5883,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.34782608695652173,
498
+ "grad_norm": 2.467388391494751,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.2226,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.35294117647058826,
505
+ "grad_norm": 2.762615442276001,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.5631,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.35805626598465473,
512
+ "grad_norm": 2.483009099960327,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.3403,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.3631713554987212,
519
+ "grad_norm": 2.626396417617798,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.5624,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.36828644501278773,
526
+ "grad_norm": 2.52079439163208,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.0151,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.3734015345268542,
533
+ "grad_norm": 2.606149196624756,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.2943,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.37851662404092073,
540
+ "grad_norm": 2.5749869346618652,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.2601,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.3836317135549872,
547
+ "grad_norm": 2.8876609802246094,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.3571,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.3887468030690537,
554
+ "grad_norm": 2.7740166187286377,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.2734,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3938618925831202,
561
+ "grad_norm": 2.7462379932403564,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.246,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3989769820971867,
568
+ "grad_norm": 2.99219012260437,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.1732,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.4040920716112532,
575
+ "grad_norm": 3.3825836181640625,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.2592,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.4092071611253197,
582
+ "grad_norm": 3.214312791824341,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.4639,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.4143222506393862,
589
+ "grad_norm": 3.0671980381011963,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.4281,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.4194373401534527,
596
+ "grad_norm": 3.599956512451172,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.6475,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.42455242966751916,
603
+ "grad_norm": 3.5274112224578857,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.9389,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.4296675191815857,
610
+ "grad_norm": 3.325232982635498,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.2739,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.43478260869565216,
617
+ "grad_norm": 2.8733978271484375,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.2412,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.4398976982097187,
624
+ "grad_norm": 2.7152678966522217,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.3306,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.44501278772378516,
631
+ "grad_norm": 1.1031886339187622,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 0.2063,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.45012787723785164,
638
+ "grad_norm": 1.2320791482925415,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 0.1947,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.45524296675191817,
645
+ "grad_norm": 2.740642786026001,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 0.7391,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.46035805626598464,
652
+ "grad_norm": 1.454041838645935,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 0.0163,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.46547314578005117,
659
+ "grad_norm": 0.48821330070495605,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 0.0089,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.47058823529411764,
666
+ "grad_norm": 1.3230316638946533,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.1831,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.47570332480818417,
673
+ "grad_norm": 1.6790002584457397,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.0349,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.48081841432225064,
680
+ "grad_norm": 0.4050397574901581,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.0087,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4859335038363171,
687
+ "grad_norm": 1.697842001914978,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 0.2403,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.49104859335038364,
694
+ "grad_norm": 0.3642440736293793,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.0087,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.4961636828644501,
701
+ "grad_norm": 9.899507522583008,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.3783,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.5012787723785166,
708
+ "grad_norm": 8.864073753356934,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 3.3658,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.5063938618925832,
715
+ "grad_norm": 5.942741394042969,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.8918,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.5115089514066496,
722
+ "grad_norm": 4.304798126220703,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.6705,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.5115089514066496,
729
+ "eval_loss": 2.1948964595794678,
730
+ "eval_runtime": 23.5471,
731
+ "eval_samples_per_second": 14.014,
732
+ "eval_steps_per_second": 3.525,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.342040646352896e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null