bbytxt commited on
Commit
78938fb
·
verified ·
1 Parent(s): 7cfd6e3

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:ebbd4b5e31bfead34129bdd1ee7bf23536f57fcc5486897ad22014acca4b3a83
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d003c7002e825ef41c4aad856914a23626c18e06fe65d388a0ad88a8770785d
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4213ee306b02bc43fc56f44629b12f882364f6be4e50771a2fd5d1388a4171f
3
  size 101184122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01b3364f73d5ceac85044b6c5eb8874b9f4a34092d5192c3b63f73733e0ca99
3
  size 101184122
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbedae35a8736e353579efafb1d9eaee766975c112bd6f697db85f21ae1fcd40
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ac64d43a9c034f6aca5b3341a3f6997f12cabd87002f2b5d38452f309266b7
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": 3.658907413482666,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.676818950930626,
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": 46.894,
374
  "eval_steps_per_second": 12.005,
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": 1.0319421939646464e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 3.6099913120269775,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.362098138747885,
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": 46.894,
374
  "eval_steps_per_second": 12.005,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.6903553299492385,
379
+ "grad_norm": 1.3157494068145752,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 3.6715,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.7038917089678511,
386
+ "grad_norm": 1.6480339765548706,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 4.1417,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.7174280879864636,
393
+ "grad_norm": 1.518749713897705,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 3.6444,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.7309644670050761,
400
+ "grad_norm": 1.8039215803146362,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 3.9769,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.7445008460236887,
407
+ "grad_norm": 1.06398606300354,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 3.6596,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.7580372250423012,
414
+ "grad_norm": 1.0259342193603516,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 3.717,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.7715736040609137,
421
+ "grad_norm": 0.9348158836364746,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 3.3873,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.7851099830795262,
428
+ "grad_norm": 1.033394455909729,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 3.5139,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.7986463620981388,
435
+ "grad_norm": 1.0691534280776978,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 3.4741,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.8121827411167513,
442
+ "grad_norm": 1.0994362831115723,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 3.5142,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.8257191201353637,
449
+ "grad_norm": 1.0791237354278564,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 3.3452,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.8392554991539763,
456
+ "grad_norm": 1.16475248336792,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 3.7296,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.8527918781725888,
463
+ "grad_norm": 1.1288127899169922,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 3.3933,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.8663282571912013,
470
+ "grad_norm": 1.2290265560150146,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 3.5753,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.8798646362098139,
477
+ "grad_norm": 1.143328070640564,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 3.6006,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.8934010152284264,
484
+ "grad_norm": 1.249060034751892,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 3.4214,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.9069373942470389,
491
+ "grad_norm": 1.3204628229141235,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 3.3819,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.9204737732656514,
498
+ "grad_norm": 1.3643982410430908,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 3.8538,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.934010152284264,
505
+ "grad_norm": 1.2954354286193848,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 3.8072,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.9475465313028765,
512
+ "grad_norm": 1.635848045349121,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 3.6974,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.961082910321489,
519
+ "grad_norm": 1.5739266872406006,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 3.8517,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.9746192893401016,
526
+ "grad_norm": 1.9741549491882324,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 4.3486,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.988155668358714,
533
+ "grad_norm": 1.0924246311187744,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 3.5943,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.0101522842639594,
540
+ "grad_norm": 1.7769662141799927,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 5.9384,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.023688663282572,
547
+ "grad_norm": 1.0755778551101685,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 3.7781,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.0372250423011844,
554
+ "grad_norm": 0.9576964974403381,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 3.274,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.0507614213197969,
561
+ "grad_norm": 1.0078204870224,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 3.5456,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.0642978003384094,
568
+ "grad_norm": 0.9900814890861511,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 3.7089,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.077834179357022,
575
+ "grad_norm": 1.0500483512878418,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 3.5293,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.0913705583756346,
582
+ "grad_norm": 1.1538033485412598,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 3.4348,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.104906937394247,
589
+ "grad_norm": 1.0635679960250854,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 3.4902,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.1184433164128595,
596
+ "grad_norm": 1.1531682014465332,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 3.5306,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.131979695431472,
603
+ "grad_norm": 1.1337559223175049,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 3.6038,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.1455160744500845,
610
+ "grad_norm": 1.1763681173324585,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 3.4732,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.1590524534686972,
617
+ "grad_norm": 1.3725019693374634,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 3.5141,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.1725888324873097,
624
+ "grad_norm": 1.287148356437683,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 3.4666,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.1861252115059222,
631
+ "grad_norm": 1.2582811117172241,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 3.5794,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.1996615905245347,
638
+ "grad_norm": 1.3983982801437378,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 3.6621,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.2131979695431472,
645
+ "grad_norm": 1.4939510822296143,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 3.6124,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.2267343485617597,
652
+ "grad_norm": 1.648148536682129,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 3.7459,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.2402707275803722,
659
+ "grad_norm": 1.8571910858154297,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 4.112,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.2538071065989849,
666
+ "grad_norm": 1.3094947338104248,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 3.7015,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.2673434856175974,
673
+ "grad_norm": 1.080057978630066,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 3.5508,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.2808798646362098,
680
+ "grad_norm": 1.052301049232483,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 3.5461,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.2944162436548223,
687
+ "grad_norm": 1.0805667638778687,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 3.672,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.3079526226734348,
694
+ "grad_norm": 1.0864343643188477,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 3.4411,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.3214890016920473,
701
+ "grad_norm": 1.0621790885925293,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 3.3916,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.3350253807106598,
708
+ "grad_norm": 1.1159321069717407,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 3.4388,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.3485617597292725,
715
+ "grad_norm": 1.1290203332901,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 3.4397,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.362098138747885,
722
+ "grad_norm": 1.1767339706420898,
723
+ "learning_rate": 0.0,
724
+ "loss": 3.4482,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.362098138747885,
729
+ "eval_loss": 3.6099913120269775,
730
+ "eval_runtime": 2.6641,
731
+ "eval_samples_per_second": 46.92,
732
+ "eval_steps_per_second": 12.011,
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": 2.066457809859379e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null