prxy5606 commited on
Commit
4c494aa
·
verified ·
1 Parent(s): 1eca768

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:c9f6e3c7ef911c610dc95634d9043277fe536287d4adefa947e354d0c7da2e75
3
  size 2373352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4ffabb34d106e54d185380cc6f7e2c5f5f3eb1369cbaaf029f04c7491ed4eb4
3
  size 2373352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e584e0406bd6336481b7410eca3c5440255dc0645d3790a682b005a77de73c9c
3
  size 4830714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb856d68a5d4a2b1b4ed3dd0014fb7364b4c0a20172f2ff1ea051ca3671d59da
3
  size 4830714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0411bc8a9071072db00892168a4adbda6be6089e070192ba9829676ee137e299
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc1f4af5d06d948911a4c3ad24cbbbbc9c2cc45f5c294e8ad4849abf0502838
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": 11.85046672821045,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.018957345971563982,
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": 100.949,
374
  "eval_steps_per_second": 25.249,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 56466800640000.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 11.812297821044922,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.037914691943127965,
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": 100.949,
374
  "eval_steps_per_second": 25.249,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.01933649289099526,
379
+ "grad_norm": 0.21670155227184296,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 11.8483,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.019715639810426542,
386
+ "grad_norm": 0.1768616884946823,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 11.8614,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.02009478672985782,
393
+ "grad_norm": 0.14872843027114868,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 11.8544,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.020473933649289098,
400
+ "grad_norm": 0.26231178641319275,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 11.8611,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.02085308056872038,
407
+ "grad_norm": 0.1851011961698532,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 11.8575,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.021232227488151657,
414
+ "grad_norm": 0.16626429557800293,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 11.8542,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.02161137440758294,
421
+ "grad_norm": 0.1764294058084488,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 11.8449,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.021990521327014217,
428
+ "grad_norm": 0.19001427292823792,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 11.8618,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.022369668246445498,
435
+ "grad_norm": 0.20055465400218964,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 11.8561,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.022748815165876776,
442
+ "grad_norm": 0.1839049756526947,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 11.8538,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.023127962085308058,
449
+ "grad_norm": 0.16656097769737244,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 11.8499,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.023507109004739336,
456
+ "grad_norm": 0.15637564659118652,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 11.8478,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.023886255924170617,
463
+ "grad_norm": 0.1506025791168213,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 11.8496,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.024265402843601895,
470
+ "grad_norm": 0.18512433767318726,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 11.8521,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.024644549763033177,
477
+ "grad_norm": 0.19561633467674255,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 11.8488,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.025023696682464455,
484
+ "grad_norm": 0.15633133053779602,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 11.8452,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.025402843601895736,
491
+ "grad_norm": 0.15324749052524567,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 11.8427,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.025781990521327014,
498
+ "grad_norm": 0.16857261955738068,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 11.845,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.026161137440758295,
505
+ "grad_norm": 0.19223137199878693,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 11.8425,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.026540284360189573,
512
+ "grad_norm": 0.19688811898231506,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 11.8418,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.02691943127962085,
519
+ "grad_norm": 0.16625766456127167,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 11.8403,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.027298578199052133,
526
+ "grad_norm": 0.1805586814880371,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 11.8356,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.02767772511848341,
533
+ "grad_norm": 0.18211770057678223,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 11.8378,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.028056872037914692,
540
+ "grad_norm": 0.1834656447172165,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 11.8259,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.02843601895734597,
547
+ "grad_norm": 0.16003456711769104,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 11.8347,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02881516587677725,
554
+ "grad_norm": 0.1905023753643036,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 11.8263,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.02919431279620853,
561
+ "grad_norm": 0.14761149883270264,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 11.8357,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.02957345971563981,
568
+ "grad_norm": 0.1856553852558136,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 11.8237,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.02995260663507109,
575
+ "grad_norm": 0.14715948700904846,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 11.8252,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.03033175355450237,
582
+ "grad_norm": 0.1759246587753296,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 11.8251,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.03071090047393365,
589
+ "grad_norm": 0.13867217302322388,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 11.8188,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.03109004739336493,
596
+ "grad_norm": 0.12833894789218903,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 11.8229,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.03146919431279621,
603
+ "grad_norm": 0.12929992377758026,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 11.8198,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.03184834123222749,
610
+ "grad_norm": 0.1879982054233551,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 11.8211,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.03222748815165877,
617
+ "grad_norm": 0.13484127819538116,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 11.8133,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.032606635071090045,
624
+ "grad_norm": 0.16426604986190796,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 11.8192,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.03298578199052133,
631
+ "grad_norm": 0.15773631632328033,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 11.8171,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.03336492890995261,
638
+ "grad_norm": 0.1757354736328125,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 11.8124,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.033744075829383886,
645
+ "grad_norm": 0.1542123258113861,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 11.8166,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.034123222748815164,
652
+ "grad_norm": 0.16527996957302094,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 11.8206,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.03450236966824644,
659
+ "grad_norm": 0.16867831349372864,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 11.8075,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.03488151658767773,
666
+ "grad_norm": 0.15023113787174225,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 11.8108,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.035260663507109005,
673
+ "grad_norm": 0.14039337635040283,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 11.7986,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03563981042654028,
680
+ "grad_norm": 0.18728798627853394,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 11.8061,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.03601895734597156,
687
+ "grad_norm": 0.21996043622493744,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 11.8135,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.036398104265402846,
694
+ "grad_norm": 0.20277753472328186,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 11.8046,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.036777251184834124,
701
+ "grad_norm": 0.18947215378284454,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 11.8009,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.0371563981042654,
708
+ "grad_norm": 0.19484518468379974,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 11.8014,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03753554502369668,
715
+ "grad_norm": 0.2266094982624054,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 11.7963,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.037914691943127965,
722
+ "grad_norm": 0.23149214684963226,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 11.7938,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.037914691943127965,
729
+ "eval_loss": 11.812297821044922,
730
+ "eval_runtime": 43.9061,
731
+ "eval_samples_per_second": 101.17,
732
+ "eval_steps_per_second": 25.304,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 112933601280000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null