prxy5606 commited on
Commit
e9fbaf8
·
verified ·
1 Parent(s): 31c427b

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:d2fc9b043e84988c3db646aef2c6719d4ea15f43076e215b9c523b11ba39f785
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93b77bbe99c46eda05d21335d34352e5d4047bd2c289ba91c160f64e45ec8a2
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92323764331c1361290e51f1ff22442563bac5588b3c8db227c2472d8398c6de
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcfd0cf5a455b8eed5db612cc91ed5f70ce7eb4d6b1485fcca0c006f8f64b70f
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:f0d4de87dbd2cceef45a9633a3f2324b50f16a7b8b6f8c58a9cdef6558adfe1e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede1e9de2e627f9aceaad433ca3d8e80a458236d1d9d360e37984ffc9bcec7d5
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": 1.2079874277114868,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.0423998304006784,
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": 5.39,
374
  "eval_steps_per_second": 1.348,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.134065922122711e+17,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1804490089416504,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.0847996608013568,
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": 5.39,
374
  "eval_steps_per_second": 1.348,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.043247827008691966,
379
+ "grad_norm": 2.945244073867798,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 4.3313,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.04409582361670553,
386
+ "grad_norm": 2.7942020893096924,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 3.9297,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.0449438202247191,
393
+ "grad_norm": 2.118166923522949,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 4.3762,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.04579181683273267,
400
+ "grad_norm": 1.9930267333984375,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 4.8376,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.04663981344074624,
407
+ "grad_norm": 2.2635605335235596,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 4.4252,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.04748781004875981,
414
+ "grad_norm": 2.0338568687438965,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 4.1499,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.048335806656773374,
421
+ "grad_norm": 2.1100118160247803,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 4.4142,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.04918380326478694,
428
+ "grad_norm": 2.1581358909606934,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 4.3231,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.05003179987280051,
435
+ "grad_norm": 2.1608479022979736,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 4.3675,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.050879796480814074,
442
+ "grad_norm": 2.024601697921753,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 4.975,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.05172779308882765,
449
+ "grad_norm": 2.0843992233276367,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 4.706,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.052575789696841214,
456
+ "grad_norm": 2.1028475761413574,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 5.2285,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.05342378630485478,
463
+ "grad_norm": 2.36572003364563,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 4.849,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.05427178291286835,
470
+ "grad_norm": 2.0823628902435303,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 5.1388,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.055119779520881915,
477
+ "grad_norm": 2.204245090484619,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 4.8233,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.05596777612889548,
484
+ "grad_norm": 2.037562608718872,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 4.6374,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.056815772736909055,
491
+ "grad_norm": 2.247715711593628,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 5.0396,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.05766376934492262,
498
+ "grad_norm": 2.378948211669922,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 5.002,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.05851176595293619,
505
+ "grad_norm": 2.3862147331237793,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 4.7315,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.059359762560949755,
512
+ "grad_norm": 2.530724287033081,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 4.9347,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.06020775916896332,
519
+ "grad_norm": 2.448453903198242,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 4.4421,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.06105575577697689,
526
+ "grad_norm": 2.2494592666625977,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 4.3259,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.06190375238499046,
533
+ "grad_norm": 2.4794130325317383,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 4.7365,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.06275174899300402,
540
+ "grad_norm": 2.7880704402923584,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 4.6844,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.0635997456010176,
547
+ "grad_norm": 2.77188777923584,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 4.9251,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.06444774220903117,
554
+ "grad_norm": 2.695709705352783,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 4.4193,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.06529573881704473,
561
+ "grad_norm": 2.6865248680114746,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 4.4448,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.0661437354250583,
568
+ "grad_norm": 2.293822765350342,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 4.9784,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.06699173203307186,
575
+ "grad_norm": 2.4043514728546143,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 4.9327,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.06783972864108544,
582
+ "grad_norm": 2.4730265140533447,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 5.0296,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.06868772524909901,
589
+ "grad_norm": 2.3908400535583496,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 5.096,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.06953572185711257,
596
+ "grad_norm": 2.6292006969451904,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 4.7537,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.07038371846512614,
603
+ "grad_norm": 2.5612385272979736,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 5.1523,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.0712317150731397,
610
+ "grad_norm": 2.547719717025757,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 4.634,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.07207971168115328,
617
+ "grad_norm": 2.726158857345581,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 4.921,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.07292770828916684,
624
+ "grad_norm": 2.6802666187286377,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 5.0294,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.07377570489718041,
631
+ "grad_norm": 2.8893790245056152,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 4.9306,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.07462370150519398,
638
+ "grad_norm": 2.926038980484009,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 5.296,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.07547169811320754,
645
+ "grad_norm": 2.9031198024749756,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 4.6424,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.07631969472122112,
652
+ "grad_norm": 2.91731595993042,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 4.9993,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.07716769132923468,
659
+ "grad_norm": 3.06075119972229,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 4.9737,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.07801568793724825,
666
+ "grad_norm": 2.9869635105133057,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 4.7087,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.07886368454526183,
673
+ "grad_norm": 3.2028849124908447,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 4.7985,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.07971168115327538,
680
+ "grad_norm": 3.2854199409484863,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 5.0808,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.08055967776128896,
687
+ "grad_norm": 3.3411152362823486,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 4.2881,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.08140767436930252,
694
+ "grad_norm": 3.3091275691986084,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 5.1494,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.08225567097731609,
701
+ "grad_norm": 3.4057445526123047,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 5.0678,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.08310366758532965,
708
+ "grad_norm": 3.694821834564209,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 5.1944,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.08395166419334323,
715
+ "grad_norm": 3.8164803981781006,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 4.8733,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.0847996608013568,
722
+ "grad_norm": 5.192181587219238,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 4.9282,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.0847996608013568,
729
+ "eval_loss": 1.1804490089416504,
730
+ "eval_runtime": 368.6207,
731
+ "eval_samples_per_second": 5.39,
732
+ "eval_steps_per_second": 1.348,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.2788643293128294e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null