ancient41 commited on
Commit
5fd79e9
·
verified ·
1 Parent(s): 0d8336f

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:c2c9369310472c78ee367b609a2159f5943d0b2051f8d0c06ba955aed0d0ca91
3
  size 224224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04537a3ab1df9d341979fcd13f94a44b3c7c07cab3cb5a834191081ed49e5ee4
3
  size 224224
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b4b2265b46763bc5ab4224b8fd6c5ec3dae5c020b1db0b392744b635fcc99f8
3
  size 458278
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa71a1a03d4c6e02d42b83d7b04ecd9255ea3b8051351699a7525a873c1535ae
3
  size 458278
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bca94231e13362e93b88d47abd489b29893b9becdb9706c9b907667d8bd20d18
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a3340464902bd64c9c898fa5a2b1da20d5bd8cea6d047e60c0f6f1c7ca8de9
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": 10.275181770324707,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.016645859342488557,
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": 469.099,
374
  "eval_steps_per_second": 117.298,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 10901565997056.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.258431434631348,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.033291718684977115,
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": 469.099,
374
  "eval_steps_per_second": 117.298,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.016978776529338328,
379
+ "grad_norm": 0.9912024736404419,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 41.1524,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.017311693716188098,
386
+ "grad_norm": 0.9454850554466248,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 41.1325,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.017644610903037868,
393
+ "grad_norm": 0.9241641163825989,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 41.1237,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.017977528089887642,
400
+ "grad_norm": 1.0917491912841797,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 41.1277,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.018310445276737412,
407
+ "grad_norm": 1.0094295740127563,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 41.1283,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.018643362463587183,
414
+ "grad_norm": 0.8367841243743896,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 41.1117,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.018976279650436953,
421
+ "grad_norm": 0.8164386749267578,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 41.111,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.019309196837286723,
428
+ "grad_norm": 0.7382983565330505,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 41.1097,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.019642114024136497,
435
+ "grad_norm": 0.5855153799057007,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 41.1029,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.019975031210986267,
442
+ "grad_norm": 0.6896238923072815,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 41.0969,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.020307948397836038,
449
+ "grad_norm": 0.6071277856826782,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 41.0983,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.020640865584685808,
456
+ "grad_norm": 0.5799134373664856,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 41.0863,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.020973782771535582,
463
+ "grad_norm": 0.5900580286979675,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 41.1057,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.021306699958385352,
470
+ "grad_norm": 0.471623033285141,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 41.0887,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.021639617145235122,
477
+ "grad_norm": 0.45357245206832886,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 41.0984,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.021972534332084893,
484
+ "grad_norm": 0.37818077206611633,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 41.0747,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.022305451518934667,
491
+ "grad_norm": 0.5794506072998047,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 41.0609,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.022638368705784437,
498
+ "grad_norm": 0.46531274914741516,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 41.0309,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.022971285892634207,
505
+ "grad_norm": 0.4518864154815674,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 41.0862,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.023304203079483977,
512
+ "grad_norm": 0.3283301889896393,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 41.0713,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.023637120266333748,
519
+ "grad_norm": 0.38813573122024536,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 41.086,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.02397003745318352,
526
+ "grad_norm": 0.38282114267349243,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 41.0621,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.024302954640033292,
533
+ "grad_norm": 0.47143545746803284,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 41.0774,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.024635871826883062,
540
+ "grad_norm": 0.5159484148025513,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 41.0864,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.024968789013732832,
547
+ "grad_norm": 0.4895094037055969,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 41.054,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.025301706200582606,
554
+ "grad_norm": 0.42369768023490906,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 41.0682,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.025634623387432377,
561
+ "grad_norm": 0.5085486173629761,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 41.0683,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.025967540574282147,
568
+ "grad_norm": 0.5052661299705505,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 41.0557,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.026300457761131917,
575
+ "grad_norm": 0.4543951451778412,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 41.0664,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.02663337494798169,
582
+ "grad_norm": 0.6069247722625732,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 41.05,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.02696629213483146,
589
+ "grad_norm": 0.6002290844917297,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 41.0476,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.02729920932168123,
596
+ "grad_norm": 0.5098062753677368,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 41.0443,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.027632126508531002,
603
+ "grad_norm": 0.5789704918861389,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 41.0635,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.027965043695380776,
610
+ "grad_norm": 0.5069387555122375,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 41.0358,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.028297960882230546,
617
+ "grad_norm": 0.6642041206359863,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 41.0331,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.028630878069080316,
624
+ "grad_norm": 0.6236996650695801,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 41.018,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.028963795255930087,
631
+ "grad_norm": 0.5848372578620911,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 41.0162,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.029296712442779857,
638
+ "grad_norm": 0.6125211119651794,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 41.0575,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.02962962962962963,
645
+ "grad_norm": 0.6385232210159302,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 41.0259,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.0299625468164794,
652
+ "grad_norm": 0.5926152467727661,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 40.999,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03029546400332917,
659
+ "grad_norm": 0.5804255604743958,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 41.0378,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.03062838119017894,
666
+ "grad_norm": 0.4631088674068451,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 41.0316,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.030961298377028715,
673
+ "grad_norm": 0.5191067457199097,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 41.0319,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.031294215563878486,
680
+ "grad_norm": 0.5826215147972107,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 41.0099,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03162713275072826,
687
+ "grad_norm": 0.5632126927375793,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 41.0116,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.031960049937578026,
694
+ "grad_norm": 0.7015792727470398,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 40.9715,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.0322929671244278,
701
+ "grad_norm": 0.6000123023986816,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 40.9717,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.03262588431127757,
708
+ "grad_norm": 0.6384497880935669,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 41.0362,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03295880149812734,
715
+ "grad_norm": 0.589424729347229,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 40.9548,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.033291718684977115,
722
+ "grad_norm": 0.8351233005523682,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 41.075,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.033291718684977115,
729
+ "eval_loss": 10.258431434631348,
730
+ "eval_runtime": 10.749,
731
+ "eval_samples_per_second": 470.648,
732
+ "eval_steps_per_second": 117.685,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 21803131994112.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null