nttx commited on
Commit
9df34f2
·
verified ·
1 Parent(s): ec4d6f0

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:bf2ecf8d33989d6b0a6acc9bf4b82957faa3c07bc9c90227e1fac8ac71c4bf2e
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302f031c4c0f27de9a3fd1e560d4f562904e08b7ff7716ac6e75b58d1e0ea647
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ae3161e48d87b0d2d7815adcb49461185666aba95d25665ab3aeea4db1af226
3
  size 148047722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859dad0c1d590f1b43293f3dc272bfcd369dc037a98928481b43b4303537a47e
3
  size 148047722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9eeb3556839924d1ce37e6fea1c62974c58ff7fb420d388f1e46e887497612f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fdcb7540926a9bbbb775e79ded590a0496a4a8277a53d9eeae2bc204ec490da
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": 2.2687292098999023,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.013594344752582926,
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": 34.654,
374
  "eval_steps_per_second": 8.665,
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": 1.30626883682304e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.2029523849487305,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.027188689505165852,
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": 34.654,
374
  "eval_steps_per_second": 8.665,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.013866231647634585,
379
+ "grad_norm": 0.6632709503173828,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 1.9544,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.014138118542686243,
386
+ "grad_norm": 0.6985868215560913,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 1.9832,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.014410005437737902,
393
+ "grad_norm": 0.6574835777282715,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 1.9303,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.01468189233278956,
400
+ "grad_norm": 0.6859593987464905,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 1.9504,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.014953779227841218,
407
+ "grad_norm": 0.7057216167449951,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 1.9376,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.015225666122892877,
414
+ "grad_norm": 0.7185929417610168,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 2.0197,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.015497553017944535,
421
+ "grad_norm": 0.7434781193733215,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 1.971,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.015769439912996192,
428
+ "grad_norm": 0.7080852389335632,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 1.988,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.016041326808047852,
435
+ "grad_norm": 0.799405574798584,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 1.863,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.01631321370309951,
442
+ "grad_norm": 0.7378050684928894,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 1.9813,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.01658510059815117,
449
+ "grad_norm": 0.8308433890342712,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 1.8692,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.016856987493202826,
456
+ "grad_norm": 0.7938002347946167,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 1.9493,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.017128874388254486,
463
+ "grad_norm": 0.7508987188339233,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 1.9912,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.017400761283306143,
470
+ "grad_norm": 0.8108996152877808,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 2.0925,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.017672648178357803,
477
+ "grad_norm": 0.8303746581077576,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 2.0514,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.01794453507340946,
484
+ "grad_norm": 0.8812360763549805,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 2.1153,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.01821642196846112,
491
+ "grad_norm": 0.876472532749176,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 2.1037,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.018488308863512777,
498
+ "grad_norm": 0.9065954089164734,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 2.0133,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.018760195758564437,
505
+ "grad_norm": 0.8889480233192444,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 2.1509,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.019032082653616094,
512
+ "grad_norm": 0.9496955275535583,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 2.0893,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.019303969548667754,
519
+ "grad_norm": 0.8941784501075745,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 2.0408,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.01957585644371941,
526
+ "grad_norm": 0.8774687051773071,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 2.0881,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.01984774333877107,
533
+ "grad_norm": 1.0062503814697266,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 2.2733,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.02011963023382273,
540
+ "grad_norm": 1.0390819311141968,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 2.1602,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.020391517128874388,
547
+ "grad_norm": 1.0490648746490479,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 2.1561,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.02066340402392605,
554
+ "grad_norm": 1.068038821220398,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 2.0451,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.020935290918977705,
561
+ "grad_norm": 1.0523394346237183,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 2.0705,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.021207177814029365,
568
+ "grad_norm": 1.1283931732177734,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 2.2912,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.021479064709081022,
575
+ "grad_norm": 1.1186964511871338,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 2.3137,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.021750951604132682,
582
+ "grad_norm": 1.12953519821167,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 2.2479,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.02202283849918434,
589
+ "grad_norm": 1.1789145469665527,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 2.1192,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.022294725394236,
596
+ "grad_norm": 1.1799867153167725,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 2.3195,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.022566612289287656,
603
+ "grad_norm": 1.145898699760437,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 2.3553,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.022838499184339316,
610
+ "grad_norm": 1.1492745876312256,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 2.3967,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.023110386079390973,
617
+ "grad_norm": 1.203434705734253,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 2.3917,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.023382272974442633,
624
+ "grad_norm": 1.2734311819076538,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 2.3567,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.02365415986949429,
631
+ "grad_norm": 1.2867752313613892,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 2.4296,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.02392604676454595,
638
+ "grad_norm": 1.3350547552108765,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 2.4295,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.024197933659597607,
645
+ "grad_norm": 1.3507503271102905,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 2.281,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.024469820554649267,
652
+ "grad_norm": 1.456315040588379,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 2.4161,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.024741707449700924,
659
+ "grad_norm": 1.5298495292663574,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 2.5141,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.025013594344752584,
666
+ "grad_norm": 1.5540664196014404,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 2.4447,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.02528548123980424,
673
+ "grad_norm": 1.6164096593856812,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 2.4986,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.0255573681348559,
680
+ "grad_norm": 1.6910641193389893,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 2.5502,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.025829255029907558,
687
+ "grad_norm": 1.7089169025421143,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 2.5604,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.026101141924959218,
694
+ "grad_norm": 1.7781983613967896,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 2.5612,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.026373028820010875,
701
+ "grad_norm": 1.8133773803710938,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 2.5704,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.026644915715062535,
708
+ "grad_norm": 1.9905413389205933,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 2.6352,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.026916802610114192,
715
+ "grad_norm": 2.2055206298828125,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 2.4121,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.027188689505165852,
722
+ "grad_norm": 2.557385206222534,
723
+ "learning_rate": 0.0,
724
+ "loss": 2.4561,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.027188689505165852,
729
+ "eval_loss": 2.2029523849487305,
730
+ "eval_runtime": 178.7527,
731
+ "eval_samples_per_second": 34.657,
732
+ "eval_steps_per_second": 8.666,
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": 2.61253767364608e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null