bbytxt commited on
Commit
e0d76ec
·
verified ·
1 Parent(s): 5dd3cde

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:bc3f280c5ca103143660266103b74a6570abc69758ce36cc9d368aab5e2dfd3a
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edc6d110c6ee168934325d7caecb6fe72f8b7a5f0db191f69923a4f2b6b101e5
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7c976ae980e9ac8047d235ccd19fef24fde2464dd53f75900c30ff396c32f10
3
  size 200345450
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c4da6af4b377f072334f8dd3d554d37172ccd9bda8566a81fdf55d5bd9929b
3
  size 200345450
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9893f6162a58573bd264360beb6b21a0956ecc0fbb3754b119b82985ca44eb13
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1ed4842887a13ecff8e3f549138986adef79ce125ddb95aca0a6f49c9263062
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d689b2d605789fff660b4cfbb1ce6889a5251953118f474a71b33d74e2d19be7
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": 5.724390029907227,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.07385524372230429,
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": 10.924,
374
  "eval_steps_per_second": 1.375,
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": 1.9110914162688e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 4.619130611419678,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.14771048744460857,
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": 10.924,
374
  "eval_steps_per_second": 1.375,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.07533234859675036,
379
+ "grad_norm": 6.688117027282715,
380
+ "learning_rate": 3.969463130731183e-06,
381
+ "loss": 3.2004,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.07680945347119646,
386
+ "grad_norm": 8.25613784790039,
387
+ "learning_rate": 3.8772424536302565e-06,
388
+ "loss": 3.8522,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.07828655834564253,
393
+ "grad_norm": 7.771860599517822,
394
+ "learning_rate": 3.782248193514766e-06,
395
+ "loss": 3.62,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.07976366322008863,
400
+ "grad_norm": 9.126646041870117,
401
+ "learning_rate": 3.684671656182497e-06,
402
+ "loss": 4.2849,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.08124076809453472,
407
+ "grad_norm": 8.893864631652832,
408
+ "learning_rate": 3.5847093477938955e-06,
409
+ "loss": 4.2011,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.0827178729689808,
414
+ "grad_norm": 7.722706317901611,
415
+ "learning_rate": 3.4825625791348093e-06,
416
+ "loss": 3.6801,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.08419497784342689,
421
+ "grad_norm": 8.404489517211914,
422
+ "learning_rate": 3.3784370602033572e-06,
423
+ "loss": 3.8903,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.08567208271787297,
428
+ "grad_norm": 8.851256370544434,
429
+ "learning_rate": 3.272542485937369e-06,
430
+ "loss": 4.1234,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.08714918759231906,
435
+ "grad_norm": 7.835949420928955,
436
+ "learning_rate": 3.165092113916688e-06,
437
+ "loss": 3.7817,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.08862629246676514,
442
+ "grad_norm": 8.80264663696289,
443
+ "learning_rate": 3.056302334890786e-06,
444
+ "loss": 4.1737,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.09010339734121123,
449
+ "grad_norm": 8.49503231048584,
450
+ "learning_rate": 2.946392236996592e-06,
451
+ "loss": 3.8425,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.0915805022156573,
456
+ "grad_norm": 8.439919471740723,
457
+ "learning_rate": 2.835583164544139e-06,
458
+ "loss": 4.0178,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.0930576070901034,
463
+ "grad_norm": 10.640103340148926,
464
+ "learning_rate": 2.724098272258584e-06,
465
+ "loss": 4.054,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.09453471196454949,
470
+ "grad_norm": 8.416254043579102,
471
+ "learning_rate": 2.6121620758762877e-06,
472
+ "loss": 4.0347,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.09601181683899557,
477
+ "grad_norm": 10.077754974365234,
478
+ "learning_rate": 2.5e-06,
479
+ "loss": 4.7311,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.09748892171344166,
484
+ "grad_norm": 10.852299690246582,
485
+ "learning_rate": 2.3878379241237136e-06,
486
+ "loss": 5.0589,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.09896602658788774,
491
+ "grad_norm": 8.857027053833008,
492
+ "learning_rate": 2.2759017277414165e-06,
493
+ "loss": 4.155,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.10044313146233383,
498
+ "grad_norm": 9.840660095214844,
499
+ "learning_rate": 2.1644168354558623e-06,
500
+ "loss": 4.542,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.1019202363367799,
505
+ "grad_norm": 10.586484909057617,
506
+ "learning_rate": 2.053607763003409e-06,
507
+ "loss": 5.1637,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.103397341211226,
512
+ "grad_norm": 10.181109428405762,
513
+ "learning_rate": 1.9436976651092143e-06,
514
+ "loss": 4.5931,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.10487444608567208,
519
+ "grad_norm": 8.879673957824707,
520
+ "learning_rate": 1.8349078860833125e-06,
521
+ "loss": 4.2358,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.10635155096011817,
526
+ "grad_norm": 9.705038070678711,
527
+ "learning_rate": 1.7274575140626318e-06,
528
+ "loss": 4.2264,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.10782865583456426,
533
+ "grad_norm": 11.851544380187988,
534
+ "learning_rate": 1.6215629397966432e-06,
535
+ "loss": 4.5553,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.10930576070901034,
540
+ "grad_norm": 11.327683448791504,
541
+ "learning_rate": 1.5174374208651913e-06,
542
+ "loss": 4.2947,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.11078286558345643,
547
+ "grad_norm": 9.12096881866455,
548
+ "learning_rate": 1.415290652206105e-06,
549
+ "loss": 4.4722,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.11225997045790251,
554
+ "grad_norm": 10.653883934020996,
555
+ "learning_rate": 1.3153283438175036e-06,
556
+ "loss": 4.6045,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.1137370753323486,
561
+ "grad_norm": 10.704031944274902,
562
+ "learning_rate": 1.217751806485235e-06,
563
+ "loss": 5.3001,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.11521418020679468,
568
+ "grad_norm": 10.759645462036133,
569
+ "learning_rate": 1.122757546369744e-06,
570
+ "loss": 4.9655,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.11669128508124077,
575
+ "grad_norm": 9.468240737915039,
576
+ "learning_rate": 1.0305368692688175e-06,
577
+ "loss": 4.4559,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.11816838995568685,
582
+ "grad_norm": 10.726446151733398,
583
+ "learning_rate": 9.412754953531664e-07,
584
+ "loss": 4.495,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.11964549483013294,
589
+ "grad_norm": 10.774774551391602,
590
+ "learning_rate": 8.551531851507186e-07,
591
+ "loss": 4.5627,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.12112259970457903,
596
+ "grad_norm": 15.364916801452637,
597
+ "learning_rate": 7.723433775328385e-07,
598
+ "loss": 6.0505,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.12259970457902511,
603
+ "grad_norm": 10.570252418518066,
604
+ "learning_rate": 6.930128404315214e-07,
605
+ "loss": 5.0273,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.1240768094534712,
610
+ "grad_norm": 10.188580513000488,
611
+ "learning_rate": 6.17321334990973e-07,
612
+ "loss": 4.7658,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.1255539143279173,
617
+ "grad_norm": 12.545642852783203,
618
+ "learning_rate": 5.454212938299256e-07,
619
+ "loss": 4.9244,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.12703101920236337,
624
+ "grad_norm": 11.229552268981934,
625
+ "learning_rate": 4.774575140626317e-07,
626
+ "loss": 4.9959,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.12850812407680945,
631
+ "grad_norm": 13.353278160095215,
632
+ "learning_rate": 4.1356686569674344e-07,
633
+ "loss": 5.5947,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.12998522895125553,
638
+ "grad_norm": 12.811745643615723,
639
+ "learning_rate": 3.538780159953348e-07,
640
+ "loss": 5.2684,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.13146233382570163,
645
+ "grad_norm": 14.855345726013184,
646
+ "learning_rate": 2.98511170358155e-07,
647
+ "loss": 5.4075,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.1329394387001477,
652
+ "grad_norm": 22.820568084716797,
653
+ "learning_rate": 2.4757783024395244e-07,
654
+ "loss": 6.2209,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.1344165435745938,
659
+ "grad_norm": 33.82524490356445,
660
+ "learning_rate": 2.0118056862137358e-07,
661
+ "loss": 9.4367,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.1358936484490399,
666
+ "grad_norm": 14.382251739501953,
667
+ "learning_rate": 1.59412823400657e-07,
668
+ "loss": 5.8712,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.13737075332348597,
673
+ "grad_norm": 14.410211563110352,
674
+ "learning_rate": 1.223587092621162e-07,
675
+ "loss": 5.3496,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.13884785819793205,
680
+ "grad_norm": 31.486698150634766,
681
+ "learning_rate": 9.00928482603669e-08,
682
+ "loss": 9.6945,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.14032496307237813,
687
+ "grad_norm": 20.718799591064453,
688
+ "learning_rate": 6.268021954544095e-08,
689
+ "loss": 7.5291,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.14180206794682423,
694
+ "grad_norm": 21.785247802734375,
695
+ "learning_rate": 4.017602850342584e-08,
696
+ "loss": 6.9029,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.1432791728212703,
701
+ "grad_norm": 30.33222770690918,
702
+ "learning_rate": 2.262559558016325e-08,
703
+ "loss": 7.52,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.1447562776957164,
708
+ "grad_norm": 33.29640197753906,
709
+ "learning_rate": 1.006426501190233e-08,
710
+ "loss": 8.3836,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.14623338257016247,
715
+ "grad_norm": 21.80366325378418,
716
+ "learning_rate": 2.5173336467135266e-09,
717
+ "loss": 7.7304,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.14771048744460857,
722
+ "grad_norm": 33.6093864440918,
723
+ "learning_rate": 0.0,
724
+ "loss": 8.8576,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.14771048744460857,
729
+ "eval_loss": 4.619130611419678,
730
+ "eval_runtime": 26.183,
731
+ "eval_samples_per_second": 10.923,
732
+ "eval_steps_per_second": 1.375,
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": 3.8221828325376e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null