prxy5605 commited on
Commit
f245ed8
·
verified ·
1 Parent(s): 7abe4eb

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:dccada3f51ca8437843e899344f99abb0bced3ff3abfa52351b6b42e86b01bd9
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:576a1fc57c8b4a85138f5312094b54476c3ed6f58d91d5855b098ddd00cb6bdd
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dca7c35c55ea71dc65c0c09b35571ea55ee8500288c7a05635cc1fa743f0c6e1
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89586263bcdd5b45ec359fa94212e69e3248afc565be3f1c2114ec4c3b845a55
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:545aa7faa16cd6d88325f232e900701a6d5e82e589ca9105f89121d1fe0cbf85
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a004d8ff38579a441a04602b2ff5b6351d6d59a459e9890d18447709b3006d7f
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": 1.7195719480514526,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.015241579027587259,
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": 13.481,
374
  "eval_steps_per_second": 3.372,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.19077308849193e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4711685180664062,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.030483158055174518,
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": 13.481,
374
  "eval_steps_per_second": 3.372,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.015546410608139003,
379
+ "grad_norm": 61.46236801147461,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 6.5024,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.01585124218869075,
386
+ "grad_norm": 18.183862686157227,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 7.4495,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.016156073769242493,
393
+ "grad_norm": 9.397269248962402,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 6.7986,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01646090534979424,
400
+ "grad_norm": 6.099393367767334,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 6.4461,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.016765736930345984,
407
+ "grad_norm": 6.682137489318848,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 7.5984,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.017070568510897728,
414
+ "grad_norm": 6.377115726470947,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 6.2782,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.017375400091449476,
421
+ "grad_norm": 5.823065757751465,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 6.1547,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01768023167200122,
428
+ "grad_norm": 8.691300392150879,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 6.4599,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.017985063252552964,
435
+ "grad_norm": 9.507842063903809,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 5.7283,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.01828989483310471,
442
+ "grad_norm": 5.431769371032715,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 5.9659,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.018594726413656455,
449
+ "grad_norm": 6.959444046020508,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 6.4109,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0188995579942082,
456
+ "grad_norm": 6.050416469573975,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 6.0308,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.019204389574759947,
463
+ "grad_norm": 4.650235176086426,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 6.0326,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.01950922115531169,
470
+ "grad_norm": 4.57441520690918,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 5.9429,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.019814052735863435,
477
+ "grad_norm": 6.164806365966797,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 6.2539,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.020118884316415182,
484
+ "grad_norm": 4.8528666496276855,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 6.0395,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.020423715896966926,
491
+ "grad_norm": 4.227317810058594,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 5.2637,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.02072854747751867,
498
+ "grad_norm": 5.101165294647217,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 6.3507,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.021033379058070414,
505
+ "grad_norm": 5.496352672576904,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 5.3826,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.021338210638622162,
512
+ "grad_norm": 4.831961154937744,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 6.2885,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.021643042219173906,
519
+ "grad_norm": 6.279645919799805,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 6.4799,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.02194787379972565,
526
+ "grad_norm": 5.281492710113525,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 6.5732,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.022252705380277397,
533
+ "grad_norm": 4.832489967346191,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 6.281,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.02255753696082914,
540
+ "grad_norm": 5.089521408081055,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 5.4511,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.022862368541380886,
547
+ "grad_norm": 5.891453742980957,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 5.7084,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.023167200121932633,
554
+ "grad_norm": 4.8378987312316895,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 5.7123,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.023472031702484377,
561
+ "grad_norm": 4.414726734161377,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 5.1287,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.02377686328303612,
568
+ "grad_norm": 5.182641983032227,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 5.1877,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.02408169486358787,
575
+ "grad_norm": 5.3193254470825195,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 5.1346,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.024386526444139613,
582
+ "grad_norm": 5.478625297546387,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 4.8609,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.024691358024691357,
589
+ "grad_norm": 5.197872161865234,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 4.3952,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.024996189605243104,
596
+ "grad_norm": 5.30072546005249,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 4.9589,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.025301021185794848,
603
+ "grad_norm": 4.756397247314453,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 4.6308,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.025605852766346592,
610
+ "grad_norm": 5.27342414855957,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 4.4653,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.02591068434689834,
617
+ "grad_norm": 4.555075645446777,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 4.3031,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.026215515927450084,
624
+ "grad_norm": 5.166381359100342,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 4.1415,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.026520347508001828,
631
+ "grad_norm": 5.405249118804932,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 4.6427,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.026825179088553575,
638
+ "grad_norm": 5.342925548553467,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 4.1941,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.02713001066910532,
645
+ "grad_norm": 5.754428863525391,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 3.8832,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.027434842249657063,
652
+ "grad_norm": 5.4184088706970215,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 3.6651,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.02773967383020881,
659
+ "grad_norm": 6.166186809539795,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 3.7098,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.028044505410760555,
666
+ "grad_norm": 5.520735263824463,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 3.2639,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.0283493369913123,
673
+ "grad_norm": 6.3266730308532715,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 3.5446,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.028654168571864046,
680
+ "grad_norm": 6.167633056640625,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 3.4253,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.02895900015241579,
687
+ "grad_norm": 6.704769134521484,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 3.8071,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.029263831732967534,
694
+ "grad_norm": 6.315314292907715,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 3.2286,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.029568663313519282,
701
+ "grad_norm": 7.417150497436523,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 3.2532,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.029873494894071026,
708
+ "grad_norm": 7.790043354034424,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.9701,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03017832647462277,
715
+ "grad_norm": 9.374876022338867,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 3.3668,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.030483158055174518,
722
+ "grad_norm": 14.421830177307129,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 3.331,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.030483158055174518,
729
+ "eval_loss": 1.4711685180664062,
730
+ "eval_runtime": 409.8203,
731
+ "eval_samples_per_second": 13.482,
732
+ "eval_steps_per_second": 3.372,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.434577118649385e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null