ancient41 commited on
Commit
5e9702c
·
verified ·
1 Parent(s): 3a2d7a6

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 sha256:10fa9391f7f6b6a68485bea22ba024a575a4dcac0c373d5bd8b7ae87ad8c7b79
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5074ba44f45aa6a35c19e555a0004ada827b5a662cd78a7fc9efab8789c3fa
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06a54c8abe41affa8203b544aed6bbfa9d6c333cc24b20a8d62c6b99ec0a9cbf
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2586538d32ce87e83d65c7cde3a29f061d7a14d57cbedee1f433b5482a92bc
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:fe0bc0936c19b8447614ea955b2e19ec27d7008cca1693fc5a9be64cecc49ae3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80b9e62f380549203b4bc196fe1b874760e21712eb62d343a4e35adf257268f6
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": 2.505044460296631,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.23837902264600716,
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": 14.089,
374
  "eval_steps_per_second": 3.542,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 6.743754247923302e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.311724901199341,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.4767580452920143,
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": 14.089,
374
  "eval_steps_per_second": 3.542,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.2431466030989273,
379
+ "grad_norm": 1.8412961959838867,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.4755,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.24791418355184744,
386
+ "grad_norm": 1.689751148223877,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.2588,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2526817640047676,
393
+ "grad_norm": 0.9649447202682495,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.1355,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.25744934445768775,
400
+ "grad_norm": 0.8039404153823853,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.256,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.2622169249106079,
407
+ "grad_norm": 0.900518000125885,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.3378,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.266984505363528,
414
+ "grad_norm": 0.8476229310035706,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.2062,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.27175208581644816,
421
+ "grad_norm": 0.8238363862037659,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.3695,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.2765196662693683,
428
+ "grad_norm": 0.7881808876991272,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.3642,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.28128724672228844,
435
+ "grad_norm": 0.7238750457763672,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.1443,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2860548271752086,
442
+ "grad_norm": 0.6919417977333069,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.1517,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2908224076281287,
449
+ "grad_norm": 0.6629623174667358,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.082,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.29558998808104886,
456
+ "grad_norm": 0.7471420764923096,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.3289,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.300357568533969,
463
+ "grad_norm": 0.6996567845344543,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.1893,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.30512514898688914,
470
+ "grad_norm": 0.811893105506897,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.4038,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.3098927294398093,
477
+ "grad_norm": 0.7495221495628357,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.111,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3146603098927294,
484
+ "grad_norm": 0.8111178874969482,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.3879,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.31942789034564956,
491
+ "grad_norm": 0.73891681432724,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.2142,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.32419547079856975,
498
+ "grad_norm": 0.7016865611076355,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.1581,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.3289630512514899,
505
+ "grad_norm": 0.820429265499115,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.0799,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.33373063170441003,
512
+ "grad_norm": 0.7954638600349426,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.0854,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.33849821215733017,
519
+ "grad_norm": 0.7249769568443298,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.0811,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.3432657926102503,
526
+ "grad_norm": 0.798295795917511,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.281,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.34803337306317045,
533
+ "grad_norm": 0.8393540978431702,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.2054,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3528009535160906,
540
+ "grad_norm": 0.820716917514801,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.182,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.3575685339690107,
547
+ "grad_norm": 0.9036383628845215,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.0523,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.36233611442193087,
554
+ "grad_norm": 0.9055408835411072,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.3064,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.367103694874851,
561
+ "grad_norm": 1.0610731840133667,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.0459,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.37187127532777114,
568
+ "grad_norm": 0.9533140659332275,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 2.1942,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3766388557806913,
575
+ "grad_norm": 0.9222361445426941,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.138,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.3814064362336114,
582
+ "grad_norm": 0.9380738139152527,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.0383,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.38617401668653156,
589
+ "grad_norm": 1.0802791118621826,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.0009,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.3909415971394517,
596
+ "grad_norm": 1.0297811031341553,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.0742,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3957091775923719,
603
+ "grad_norm": 1.0209712982177734,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.2836,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.40047675804529204,
610
+ "grad_norm": 1.1667689085006714,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.0793,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.4052443384982122,
617
+ "grad_norm": 1.1458278894424438,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.1959,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.4100119189511323,
624
+ "grad_norm": 1.1719489097595215,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.0824,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.41477949940405245,
631
+ "grad_norm": 1.2250354290008545,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.5144,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.4195470798569726,
638
+ "grad_norm": 1.2479459047317505,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.1278,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.42431466030989273,
645
+ "grad_norm": 1.448906660079956,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.3074,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.42908224076281287,
652
+ "grad_norm": 1.4189363718032837,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.4023,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.433849821215733,
659
+ "grad_norm": 1.4955360889434814,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.1318,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.43861740166865315,
666
+ "grad_norm": 1.3838410377502441,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.0099,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.4433849821215733,
673
+ "grad_norm": 1.5779086351394653,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.5704,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.44815256257449343,
680
+ "grad_norm": 1.6373097896575928,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 2.3962,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.45292014302741357,
687
+ "grad_norm": 1.5908904075622559,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.1469,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.4576877234803337,
694
+ "grad_norm": 1.9041376113891602,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.6006,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.46245530393325385,
701
+ "grad_norm": 2.09298038482666,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.3567,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.46722288438617404,
708
+ "grad_norm": 1.851805329322815,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.1391,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.4719904648390942,
715
+ "grad_norm": 2.135078191757202,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.4175,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.4767580452920143,
722
+ "grad_norm": 3.424588203430176,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 2.4322,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.4767580452920143,
729
+ "eval_loss": 2.311724901199341,
730
+ "eval_runtime": 25.1495,
731
+ "eval_samples_per_second": 14.076,
732
+ "eval_steps_per_second": 3.539,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.3521059512005427e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null