prxy5608 commited on
Commit
656125f
·
verified ·
1 Parent(s): b24b46f

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:a61e8e43fd4686f3af4fd4ac114b6f2459dbdcfa3f32df97354157c30d3e5693
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65cec212398227140b8989623481ab37487c9b53416d779634a664690e45cbee
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:048369ea45089f1d6f761376e2a0c33472ec4f6a631b6ab7091912c756a3a1f7
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bac2b82409fa43c456cf3d31017f8e258b58436192c672a51e99e3b5bc794ae
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29573f8c199ad02eb0daaa0c8a71a263ea8b6ad5e3f1b854343bd69c4fa00e61
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c40f3983076c2e863048ec2e7bc2d69d61718db08626b7ba1c1891aec591c916
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": 2.8597769737243652,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.1504890895410083,
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": 12.864,
374
  "eval_steps_per_second": 3.216,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 7.617993572666573e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.7928898334503174,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.3009781790820166,
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": 12.864,
374
  "eval_steps_per_second": 3.216,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.15349887133182843,
379
+ "grad_norm": 0.9883130788803101,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.1225,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.1565086531226486,
386
+ "grad_norm": 1.146127462387085,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.7079,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.1595184349134688,
393
+ "grad_norm": 0.7247859239578247,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.4953,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.16252821670428894,
400
+ "grad_norm": 0.6606523394584656,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 2.6936,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.1655379984951091,
407
+ "grad_norm": 0.661456286907196,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 2.6561,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.16854778028592926,
414
+ "grad_norm": 0.6059918999671936,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 2.529,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.17155756207674944,
421
+ "grad_norm": 0.7299861311912537,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 2.8652,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.1745673438675696,
428
+ "grad_norm": 0.6570218205451965,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 2.6003,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.17757712565838976,
435
+ "grad_norm": 0.7697155475616455,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 2.9703,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.18058690744920994,
442
+ "grad_norm": 0.8205830454826355,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 2.719,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.1835966892400301,
449
+ "grad_norm": 0.8287568092346191,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 2.7445,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.18660647103085026,
456
+ "grad_norm": 0.7720220685005188,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 2.6071,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.18961625282167044,
463
+ "grad_norm": 0.8769961595535278,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 2.9422,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.1926260346124906,
470
+ "grad_norm": 0.7806358337402344,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 2.7808,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.19563581640331076,
477
+ "grad_norm": 0.7959004044532776,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 2.6023,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.1986455981941309,
484
+ "grad_norm": 0.9200003147125244,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 2.8079,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.2016553799849511,
491
+ "grad_norm": 0.9827006459236145,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 2.9431,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.20466516177577126,
498
+ "grad_norm": 0.9591490626335144,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 2.7521,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.2076749435665914,
505
+ "grad_norm": 0.9347128868103027,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 2.6955,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.2106847253574116,
512
+ "grad_norm": 0.8477599620819092,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 2.8735,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.21369450714823177,
519
+ "grad_norm": 0.8589199781417847,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 2.7021,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.21670428893905191,
526
+ "grad_norm": 0.8839547634124756,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 2.725,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.2197140707298721,
533
+ "grad_norm": 1.0816020965576172,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 2.9448,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.22272385252069224,
540
+ "grad_norm": 0.9550137519836426,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 2.673,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.22573363431151242,
547
+ "grad_norm": 1.0094174146652222,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 2.6478,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.2287434161023326,
554
+ "grad_norm": 0.9577383995056152,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 2.949,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.23175319789315274,
561
+ "grad_norm": 1.0763578414916992,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 2.752,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.23476297968397292,
568
+ "grad_norm": 1.019482970237732,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 3.0192,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.23777276147479307,
575
+ "grad_norm": 1.2120007276535034,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 2.958,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.24078254326561324,
582
+ "grad_norm": 1.0528912544250488,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 2.6808,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.24379232505643342,
589
+ "grad_norm": 1.070916771888733,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 2.8994,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.24680210684725357,
596
+ "grad_norm": 0.9918401837348938,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 2.6755,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.24981188863807374,
603
+ "grad_norm": 1.4494421482086182,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 2.9853,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.2528216704288939,
610
+ "grad_norm": 1.0939158201217651,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 2.7875,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.2558314522197141,
617
+ "grad_norm": 1.1803234815597534,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 2.87,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.2588412340105342,
624
+ "grad_norm": 1.224190354347229,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 2.7292,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.2618510158013544,
631
+ "grad_norm": 1.1455833911895752,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 2.7313,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.26486079759217457,
638
+ "grad_norm": 1.1967684030532837,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 2.8791,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.26787057938299474,
645
+ "grad_norm": 1.4523427486419678,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 2.8266,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.2708803611738149,
652
+ "grad_norm": 1.6074488162994385,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 2.7747,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.27389014296463504,
659
+ "grad_norm": 1.4523072242736816,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 2.9463,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.2768999247554552,
666
+ "grad_norm": 1.4732896089553833,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 2.864,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.2799097065462754,
673
+ "grad_norm": 1.4440211057662964,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 2.5142,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.28291948833709557,
680
+ "grad_norm": 1.569728970527649,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 3.1005,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.28592927012791575,
687
+ "grad_norm": 1.6300673484802246,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 2.9026,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.28893905191873587,
694
+ "grad_norm": 1.6838175058364868,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 2.9086,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.29194883370955604,
701
+ "grad_norm": 1.7202688455581665,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 2.7964,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.2949586155003762,
708
+ "grad_norm": 1.8333368301391602,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 2.7565,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.2979683972911964,
715
+ "grad_norm": 1.8898142576217651,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 2.7308,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.3009781790820166,
722
+ "grad_norm": 3.0437440872192383,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 3.1335,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.3009781790820166,
729
+ "eval_loss": 2.7928898334503174,
730
+ "eval_runtime": 43.5272,
731
+ "eval_samples_per_second": 12.866,
732
+ "eval_steps_per_second": 3.216,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.5235987145333146e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null