0x1202 commited on
Commit
a55f22f
·
verified ·
1 Parent(s): f277b1d

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:f110e84c6997f327eb1b6bb32aeed494b264714b1c55680152da1adc7311be71
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4700ae43f3f5928377fc55cdbead5db5360580c6fd61b83a9fc5b049067a6814
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da60e36f0bb3e468245e8a15bfc5b92d72855806b830f942e447c06c9fc5b972
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8645bfcdaef5266ad620a1292c37b3cc476ad9150e3aa902e7b1886133ee014b
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1903acd70de7bc852753b74df13aacce315ef1faa4c265885aec24b415cdc9d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:255939827140ca0c6d7d5bb1e227a6b55461325642f39c362c0571a4b2967795
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": 2.0653555393218994,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.03278688524590164,
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": 49.645,
374
  "eval_steps_per_second": 12.426,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.0719067958673408e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.939498782157898,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.06557377049180328,
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": 49.645,
374
  "eval_steps_per_second": 12.426,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.03344262295081967,
379
+ "grad_norm": 1.7057262659072876,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.8153,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.03409836065573771,
386
+ "grad_norm": 1.52045476436615,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.84,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.03475409836065574,
393
+ "grad_norm": 1.2717903852462769,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.8603,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.03540983606557377,
400
+ "grad_norm": 0.9368915557861328,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.8198,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.036065573770491806,
407
+ "grad_norm": 0.7638617753982544,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.8271,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.036721311475409836,
414
+ "grad_norm": 0.7003270387649536,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.7082,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.037377049180327866,
421
+ "grad_norm": 0.6691592335700989,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.6327,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.0380327868852459,
428
+ "grad_norm": 0.6497421264648438,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.6789,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.038688524590163934,
435
+ "grad_norm": 0.6695832014083862,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.7499,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.03934426229508197,
442
+ "grad_norm": 0.6742534041404724,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.7251,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.04,
449
+ "grad_norm": 0.6942402124404907,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.7845,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.04065573770491803,
456
+ "grad_norm": 0.6851775050163269,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.7387,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.04131147540983607,
463
+ "grad_norm": 0.7770962715148926,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.8634,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.0419672131147541,
470
+ "grad_norm": 0.6991023421287537,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.7691,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.04262295081967213,
477
+ "grad_norm": 0.7185125350952148,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.6845,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.043278688524590166,
484
+ "grad_norm": 0.7190847992897034,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.6519,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.043934426229508196,
491
+ "grad_norm": 0.7488616704940796,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.7423,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.04459016393442623,
498
+ "grad_norm": 0.7755244970321655,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.8318,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.04524590163934426,
505
+ "grad_norm": 0.8398361802101135,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.7331,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.04590163934426229,
512
+ "grad_norm": 0.8223381042480469,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.7701,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.04655737704918033,
519
+ "grad_norm": 0.8144294023513794,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.8039,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.04721311475409836,
526
+ "grad_norm": 0.884468138217926,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.8268,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.04786885245901639,
533
+ "grad_norm": 0.9266506433486938,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.8342,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.04852459016393443,
540
+ "grad_norm": 0.9367057085037231,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.7206,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.04918032786885246,
547
+ "grad_norm": 1.0088722705841064,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.7369,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.049836065573770495,
554
+ "grad_norm": 1.0950847864151,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.8555,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.050491803278688525,
561
+ "grad_norm": 1.1527807712554932,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.8371,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.051147540983606556,
568
+ "grad_norm": 1.2773011922836304,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.9268,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.05180327868852459,
575
+ "grad_norm": 1.1889195442199707,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.7625,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.05245901639344262,
582
+ "grad_norm": 1.2905858755111694,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.68,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.05311475409836065,
589
+ "grad_norm": 1.3566590547561646,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.7321,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.05377049180327869,
596
+ "grad_norm": 1.4779900312423706,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.9474,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.05442622950819672,
603
+ "grad_norm": 1.6690576076507568,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.9548,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.05508196721311476,
610
+ "grad_norm": 1.5478459596633911,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.7377,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.05573770491803279,
617
+ "grad_norm": 1.7774358987808228,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.9184,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.05639344262295082,
624
+ "grad_norm": 1.7999390363693237,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.04,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.057049180327868855,
631
+ "grad_norm": 1.919732689857483,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.0443,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.057704918032786885,
638
+ "grad_norm": 1.9718799591064453,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.0426,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.058360655737704915,
645
+ "grad_norm": 2.0534744262695312,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.0369,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.05901639344262295,
652
+ "grad_norm": 2.051954746246338,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.9544,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.05967213114754098,
659
+ "grad_norm": 2.204108476638794,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.948,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.06032786885245902,
666
+ "grad_norm": 2.153517484664917,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.1349,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.06098360655737705,
673
+ "grad_norm": 2.321669578552246,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.9175,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.06163934426229508,
680
+ "grad_norm": 2.6689982414245605,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.2021,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.06229508196721312,
687
+ "grad_norm": 2.4535908699035645,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.1704,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.06295081967213115,
694
+ "grad_norm": 2.312746524810791,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.9127,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.06360655737704918,
701
+ "grad_norm": 3.779184341430664,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.1832,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.06426229508196721,
708
+ "grad_norm": 3.2187552452087402,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.1398,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.06491803278688525,
715
+ "grad_norm": 3.261251449584961,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.118,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.06557377049180328,
722
+ "grad_norm": 4.284909248352051,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.6812,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.06557377049180328,
729
+ "eval_loss": 1.939498782157898,
730
+ "eval_runtime": 51.777,
731
+ "eval_samples_per_second": 49.617,
732
+ "eval_steps_per_second": 12.419,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.1438135917346816e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null