aleegis09 commited on
Commit
3083dd5
·
verified ·
1 Parent(s): 1205e68

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 sha256:8cfb71a3c2843a7fb5f5ce7001ad79ae1a51f408dc08e1e687b4438dba7a613f
3
  size 121155320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b43164046e5888d58c3aa375b7b2f433a850a20197f5b7609810bf16f9b3fa
3
  size 121155320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75a9b3e7c5b3c6c4fc6f53b7f70ce221266241137ae14139bd98a7fdaa4f30ae
3
  size 61896852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ffa9a4b8fddbba2eb1821fa57c3e0c30160d54b5ed9273b596f0c6bd49c023
3
  size 61896852
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:805ecd31f31d4682c5507cb39e3894a871dcb6dec4f2e0c5390afec48e5bf466
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cca217c1bf16069004b0b887dd236df44ea031841243328684fc122b5a14ac
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": 1.7528727054595947,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.25252525252525254,
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": 60.511,
374
  "eval_steps_per_second": 15.218,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3329388183552000.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.673848271369934,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.5050505050505051,
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": 60.511,
374
  "eval_steps_per_second": 15.218,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.25757575757575757,
379
+ "grad_norm": 1.2490203380584717,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.75,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.26262626262626265,
386
+ "grad_norm": 0.9804388880729675,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.7115,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2676767676767677,
393
+ "grad_norm": 0.7740570902824402,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.7264,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.2727272727272727,
400
+ "grad_norm": 0.6553235650062561,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.7284,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.2777777777777778,
407
+ "grad_norm": 0.6601061820983887,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.6666,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.2828282828282828,
414
+ "grad_norm": 0.6838630437850952,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.7001,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2878787878787879,
421
+ "grad_norm": 0.7081226110458374,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.6359,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.29292929292929293,
428
+ "grad_norm": 0.6920811533927917,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.7222,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.29797979797979796,
435
+ "grad_norm": 0.6932616829872131,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.6801,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.30303030303030304,
442
+ "grad_norm": 0.6817681193351746,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.6867,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.30808080808080807,
449
+ "grad_norm": 0.6873700618743896,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.6937,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.31313131313131315,
456
+ "grad_norm": 0.7055866718292236,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.6666,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.3181818181818182,
463
+ "grad_norm": 0.6892226338386536,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.7111,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.32323232323232326,
470
+ "grad_norm": 0.6525599956512451,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.6603,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.3282828282828283,
477
+ "grad_norm": 0.6676272749900818,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.6603,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3333333333333333,
484
+ "grad_norm": 0.68507319688797,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.6492,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.3383838383838384,
491
+ "grad_norm": 0.654543399810791,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.7116,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.3434343434343434,
498
+ "grad_norm": 0.6445846557617188,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.7001,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.3484848484848485,
505
+ "grad_norm": 0.660938024520874,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.6993,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.35353535353535354,
512
+ "grad_norm": 0.6602575778961182,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.6992,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.35858585858585856,
519
+ "grad_norm": 0.6613306999206543,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.6887,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.36363636363636365,
526
+ "grad_norm": 0.6551235318183899,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.6597,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.3686868686868687,
533
+ "grad_norm": 0.6808748841285706,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.6926,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.37373737373737376,
540
+ "grad_norm": 0.6841230392456055,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.6876,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.3787878787878788,
547
+ "grad_norm": 0.702394962310791,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.664,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.3838383838383838,
554
+ "grad_norm": 0.719436764717102,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.6915,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3888888888888889,
561
+ "grad_norm": 0.7273593544960022,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.6838,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3939393939393939,
568
+ "grad_norm": 0.7527819275856018,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.7053,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.398989898989899,
575
+ "grad_norm": 0.7678869366645813,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.7477,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.40404040404040403,
582
+ "grad_norm": 0.7475170493125916,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.6924,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.4090909090909091,
589
+ "grad_norm": 0.7630130648612976,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.6604,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.41414141414141414,
596
+ "grad_norm": 0.7588295936584473,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.7821,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.41919191919191917,
603
+ "grad_norm": 0.7793270945549011,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.6746,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.42424242424242425,
610
+ "grad_norm": 0.813008725643158,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.8024,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.4292929292929293,
617
+ "grad_norm": 0.7864987254142761,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.6815,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.43434343434343436,
624
+ "grad_norm": 0.8113416433334351,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.6845,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.4393939393939394,
631
+ "grad_norm": 0.8136469125747681,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.7042,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.4444444444444444,
638
+ "grad_norm": 0.8281291127204895,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.6419,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.4494949494949495,
645
+ "grad_norm": 0.8532263040542603,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.6778,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.45454545454545453,
652
+ "grad_norm": 0.879052460193634,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.7372,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.4595959595959596,
659
+ "grad_norm": 0.875851571559906,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.659,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.46464646464646464,
666
+ "grad_norm": 0.9393147230148315,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.7725,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.4696969696969697,
673
+ "grad_norm": 0.9405022263526917,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.7574,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.47474747474747475,
680
+ "grad_norm": 0.9430553913116455,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.6683,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4797979797979798,
687
+ "grad_norm": 0.9621241092681885,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.6864,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.48484848484848486,
694
+ "grad_norm": 1.0094877481460571,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.7532,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.4898989898989899,
701
+ "grad_norm": 1.0817221403121948,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.6942,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.494949494949495,
708
+ "grad_norm": 1.2114548683166504,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.7071,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.5,
715
+ "grad_norm": 0.7440630197525024,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.644,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.5050505050505051,
722
+ "grad_norm": 0.7109785676002502,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 1.6207,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.5050505050505051,
729
+ "eval_loss": 1.673848271369934,
730
+ "eval_runtime": 5.5217,
731
+ "eval_samples_per_second": 60.489,
732
+ "eval_steps_per_second": 15.213,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6658776367104000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null