0x1202 commited on
Commit
a07649e
·
verified ·
1 Parent(s): 4c84332

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 sha256:345b9518ae8d124030a175051f3e3b78c479fe3a053d3f07a81e5191f3078e70
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f25c02ee5c751f7e7ea99a6f56a59e1a554233a2ec6a45fa544d1d43ac1a9961
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1225f52c0bbbe57e4f5ff991c47c3c4155718a0d441d8646d89563d1cc96565a
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0142573320c726bed3d8c39d6fcce386db2e2c748abfe6f13d3913905b3bb3bd
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61bb29cb2d38cc9e6e29a6d21c70725c65e6b4cbd88499235aca17d234f2fd54
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c4991eac2b03cc767d5f50af9b5cd95e54a7a354393713a10b8a55e58cd30c
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": 1.3399333953857422,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.034638032559750606,
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": 13.888,
374
  "eval_steps_per_second": 3.473,
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": 1.2095348834991455,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06927606511950121,
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": 13.888,
374
  "eval_steps_per_second": 3.473,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03533079321094562,
379
+ "grad_norm": 0.7020105719566345,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.1306,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03602355386214063,
386
+ "grad_norm": 0.6428791880607605,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.223,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.036716314513335645,
393
+ "grad_norm": 0.4771263599395752,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.2416,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03740907516453065,
400
+ "grad_norm": 0.4031830430030823,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.1267,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.03810183581572567,
407
+ "grad_norm": 0.3610057830810547,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.1811,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.038794596466920676,
414
+ "grad_norm": 0.3261217176914215,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.1656,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.03948735711811569,
421
+ "grad_norm": 0.31414860486984253,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.2253,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0401801177693107,
428
+ "grad_norm": 0.31035324931144714,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.1939,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.040872878420505715,
435
+ "grad_norm": 0.2923867106437683,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.2033,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.04156563907170073,
442
+ "grad_norm": 0.3010156750679016,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.1441,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.04225839972289574,
449
+ "grad_norm": 0.3054508864879608,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.0527,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.042951160374090754,
456
+ "grad_norm": 0.3022181987762451,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.1468,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04364392102528576,
463
+ "grad_norm": 0.3066895306110382,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.1173,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.04433668167648078,
470
+ "grad_norm": 0.271780401468277,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.0944,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.045029442327675785,
477
+ "grad_norm": 0.2763840854167938,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.0566,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.0457222029788708,
484
+ "grad_norm": 0.291381299495697,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.1169,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.046414963630065816,
491
+ "grad_norm": 0.2843344211578369,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.0898,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.047107724281260824,
498
+ "grad_norm": 0.2964484691619873,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.1141,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.04780048493245584,
505
+ "grad_norm": 0.3068453371524811,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.1335,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.04849324558365085,
512
+ "grad_norm": 0.32353049516677856,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.1877,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04918600623484586,
519
+ "grad_norm": 0.3313841223716736,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.2017,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04987876688604087,
526
+ "grad_norm": 0.33044734597206116,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.1807,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.050571527537235886,
533
+ "grad_norm": 0.36810123920440674,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.2227,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.051264288188430894,
540
+ "grad_norm": 0.3565467596054077,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.1981,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.05195704883962591,
547
+ "grad_norm": 0.37128183245658875,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.2685,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.052649809490820924,
554
+ "grad_norm": 0.3571989834308624,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.1666,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.05334257014201593,
561
+ "grad_norm": 0.3861614763736725,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.1589,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.05403533079321095,
568
+ "grad_norm": 0.40964120626449585,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.1865,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.054728091444405956,
575
+ "grad_norm": 0.42549365758895874,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.1846,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05542085209560097,
582
+ "grad_norm": 0.44472768902778625,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.2405,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05611361274679598,
589
+ "grad_norm": 0.45762962102890015,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.2113,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.056806373397990995,
596
+ "grad_norm": 0.466031014919281,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.2158,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.057499134049186,
603
+ "grad_norm": 0.5040780901908875,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2898,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.05819189470038102,
610
+ "grad_norm": 0.5373992323875427,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.2256,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.05888465535157603,
617
+ "grad_norm": 0.5588688254356384,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.2354,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.05957741600277104,
624
+ "grad_norm": 0.6001823544502258,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.2763,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.06027017665396606,
631
+ "grad_norm": 0.6140657067298889,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.2977,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.060962937305161065,
638
+ "grad_norm": 0.5989546775817871,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.2141,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.06165569795635608,
645
+ "grad_norm": 0.6264601945877075,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.2107,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.06234845860755109,
652
+ "grad_norm": 0.721250057220459,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.2086,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.0630412192587461,
659
+ "grad_norm": 0.7749258875846863,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.2258,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.06373397990994112,
666
+ "grad_norm": 0.7340646982192993,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 0.9685,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06442674056113613,
673
+ "grad_norm": 0.8841552138328552,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.2315,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.06511950121233114,
680
+ "grad_norm": 0.9299079179763794,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.1874,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.06581226186352615,
687
+ "grad_norm": 0.9567759037017822,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.2052,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.06650502251472117,
694
+ "grad_norm": 1.1123799085617065,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.2805,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06719778316591618,
701
+ "grad_norm": 1.173805832862854,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.2049,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.06789054381711118,
708
+ "grad_norm": 1.3823316097259521,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.4555,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.0685833044683062,
715
+ "grad_norm": 1.2791736125946045,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.4476,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06927606511950121,
722
+ "grad_norm": 1.7184642553329468,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.3192,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06927606511950121,
729
+ "eval_loss": 1.2095348834991455,
730
+ "eval_runtime": 174.9548,
731
+ "eval_samples_per_second": 13.895,
732
+ "eval_steps_per_second": 3.475,
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