nttx commited on
Commit
743cd39
1 Parent(s): 0d55d2d

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 sha256:278990446bab1cdffbf4c001bec95f2f7be4cb4c16f43e682f7fa9bda638c70e
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3332484fe96b34b8709e1cbae737aecc86d12a053f144e53bd26ae7fbfeebb
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6e25ba615e02934b2d2407cd1437fc29093d0eb7fdbd1e8695c536501e1208b
3
  size 90365754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9835f15ffc32b8058868736c4a91b14b0a2c3639113800db15b7e8cd9a032d25
3
  size 90365754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2be76e4fee4097cada590845fe5219d0db665195c1d6c0403905e02c2ca822a5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422ee165b065ef8fdb0fb3f8c749903825e9f08a05ccd3ba0c25f087212f6104
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 4.4282355308532715,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.016046856821920006,
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": 46.016,
374
  "eval_steps_per_second": 11.504,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 9677225695641600.0,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.5903985500335693,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.03209371364384001,
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": 46.016,
374
  "eval_steps_per_second": 11.504,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.016367793958358405,
379
+ "grad_norm": 24.92586326599121,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 3.9654,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.016688731094796808,
386
+ "grad_norm": 24.382604598999023,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 3.8923,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.017009668231235207,
393
+ "grad_norm": 24.6019229888916,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 3.6808,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.017330605367673606,
400
+ "grad_norm": 24.33039093017578,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 3.7393,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.01765154250411201,
407
+ "grad_norm": 24.681549072265625,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 3.5747,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.017972479640550407,
414
+ "grad_norm": 24.564939498901367,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 3.573,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.018293416776988806,
421
+ "grad_norm": 23.479808807373047,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 3.4547,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.01861435391342721,
428
+ "grad_norm": 25.647430419921875,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 3.5706,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.018935291049865608,
435
+ "grad_norm": 23.934444427490234,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 3.3241,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.019256228186304007,
442
+ "grad_norm": 23.319473266601562,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 3.3996,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.019577165322742406,
449
+ "grad_norm": 23.8126220703125,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 3.0784,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.01989810245918081,
456
+ "grad_norm": 24.619556427001953,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 3.4374,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.020219039595619208,
463
+ "grad_norm": 23.282445907592773,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 3.1921,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.020539976732057607,
470
+ "grad_norm": 23.131887435913086,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 3.1839,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.02086091386849601,
477
+ "grad_norm": 24.023595809936523,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 2.9598,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.02118185100493441,
484
+ "grad_norm": 23.428220748901367,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 3.1564,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.021502788141372808,
491
+ "grad_norm": 22.029972076416016,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 2.8426,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.02182372527781121,
498
+ "grad_norm": 23.444753646850586,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 2.7818,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.02214466241424961,
505
+ "grad_norm": 23.392112731933594,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 2.8383,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.02246559955068801,
512
+ "grad_norm": 24.041671752929688,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 3.0414,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.022786536687126407,
519
+ "grad_norm": 21.68594741821289,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 2.873,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.02310747382356481,
526
+ "grad_norm": 21.509824752807617,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 2.7585,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.02342841096000321,
533
+ "grad_norm": 21.97166633605957,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 2.7142,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.023749348096441608,
540
+ "grad_norm": 21.628463745117188,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 2.8777,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.02407028523288001,
547
+ "grad_norm": 22.004776000976562,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 2.8746,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02439122236931841,
554
+ "grad_norm": 21.029932022094727,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 2.8362,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.02471215950575681,
561
+ "grad_norm": 20.30879020690918,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 2.6938,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.02503309664219521,
568
+ "grad_norm": 20.107864379882812,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 2.6287,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.02535403377863361,
575
+ "grad_norm": 21.4448299407959,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 2.6291,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.02567497091507201,
582
+ "grad_norm": 20.82808494567871,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 3.0268,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.025995908051510412,
589
+ "grad_norm": 20.990262985229492,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 2.806,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.02631684518794881,
596
+ "grad_norm": 19.37321662902832,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 2.5534,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.02663778232438721,
603
+ "grad_norm": 20.37537956237793,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 2.766,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.02695871946082561,
610
+ "grad_norm": 20.045385360717773,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 2.6121,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.027279656597264012,
617
+ "grad_norm": 20.654422760009766,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 2.8861,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.02760059373370241,
624
+ "grad_norm": 20.056547164916992,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 2.8262,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02792153087014081,
631
+ "grad_norm": 20.1599063873291,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 2.7126,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.028242468006579213,
638
+ "grad_norm": 20.382301330566406,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 3.0595,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.02856340514301761,
645
+ "grad_norm": 20.944210052490234,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 2.8264,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.02888434227945601,
652
+ "grad_norm": 21.320999145507812,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 2.9996,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.029205279415894413,
659
+ "grad_norm": 21.694704055786133,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 2.9851,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.029526216552332812,
666
+ "grad_norm": 21.299489974975586,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 2.8274,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.02984715368877121,
673
+ "grad_norm": 20.7717342376709,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 3.2581,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.03016809082520961,
680
+ "grad_norm": 22.040687561035156,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 2.9888,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.030489027961648013,
687
+ "grad_norm": 22.77414321899414,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 3.0421,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.030809965098086412,
694
+ "grad_norm": 24.892927169799805,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 3.1848,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.03113090223452481,
701
+ "grad_norm": 23.968238830566406,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 3.1579,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.031451839370963214,
708
+ "grad_norm": 26.281328201293945,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 3.3636,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.03177277650740161,
715
+ "grad_norm": 26.528987884521484,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 4.1474,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.03209371364384001,
722
+ "grad_norm": 33.00212860107422,
723
+ "learning_rate": 0.0,
724
+ "loss": 4.9432,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.03209371364384001,
729
+ "eval_loss": 2.5903985500335693,
730
+ "eval_runtime": 114.0548,
731
+ "eval_samples_per_second": 46.013,
732
+ "eval_steps_per_second": 11.503,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.93544513912832e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null