aleegis11 commited on
Commit
0843cb5
·
verified ·
1 Parent(s): c93594a

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 sha256:3ab36d31728e4225792ed6347fc6f5e685c16f5e003e3a094a4c0dcca36ac356
3
  size 295488936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7513115fc8bc9b244a6eafe69d6aaf5a0123d360a20341ace3ab6df217f3e2e
3
  size 295488936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97395a408e961d0fc617e6a79053047648bfbe3efed83fd04bccbaf64d02b061
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:342c045d8debdb5cb1aa66bc73ce862a75058a8f0794d1f6aa3f4090832ce746
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcd3cca9800e06d2ba140317ea89e8331ed28811b31ba95ea10d2e78e40728ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61549609e2ca23da7f58c7bd203b4a34c8b00bce2992e39107ea3d17a210cb89
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": 1.2816766500473022,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.005578333751708364,
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": 33.156,
374
  "eval_steps_per_second": 8.291,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 1.39474174476288e+16,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2055939435958862,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.011156667503416729,
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": 33.156,
374
  "eval_steps_per_second": 8.291,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.005689900426742532,
379
+ "grad_norm": 0.87342369556427,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 1.7642,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.005801467101776699,
386
+ "grad_norm": 0.776253879070282,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 1.697,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.005913033776810866,
393
+ "grad_norm": 0.6793281435966492,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 1.5065,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.006024600451845034,
400
+ "grad_norm": 0.5906603932380676,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.4913,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.006136167126879201,
407
+ "grad_norm": 0.5672029852867126,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.2197,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.006247733801913368,
414
+ "grad_norm": 0.593641459941864,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.2856,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.006359300476947536,
421
+ "grad_norm": 0.5828561782836914,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.4526,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.006470867151981703,
428
+ "grad_norm": 0.5753366351127625,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.4999,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.00658243382701587,
435
+ "grad_norm": 0.5516051054000854,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.3871,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.006694000502050037,
442
+ "grad_norm": 0.5935094952583313,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.3386,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.006805567177084205,
449
+ "grad_norm": 0.5750835537910461,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.3795,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.006917133852118372,
456
+ "grad_norm": 0.5868992805480957,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.3926,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.007028700527152539,
463
+ "grad_norm": 0.5295293927192688,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.3573,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.007140267202186707,
470
+ "grad_norm": 0.5167469382286072,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.3363,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.007251833877220874,
477
+ "grad_norm": 0.5310781598091125,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.2901,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.007363400552255041,
484
+ "grad_norm": 0.5497135519981384,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.3969,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.007474967227289209,
491
+ "grad_norm": 0.5470055937767029,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.1672,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.007586533902323376,
498
+ "grad_norm": 0.5302481651306152,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.3114,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.007698100577357543,
505
+ "grad_norm": 0.5234085321426392,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.2662,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.007809667252391711,
512
+ "grad_norm": 0.5368407368659973,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.3666,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.007921233927425877,
519
+ "grad_norm": 0.5434086322784424,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.2133,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.008032800602460045,
526
+ "grad_norm": 0.5254490375518799,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.3812,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.008144367277494213,
533
+ "grad_norm": 0.5242455005645752,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.0911,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.008255933952528379,
540
+ "grad_norm": 0.6389315724372864,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.2935,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.008367500627562547,
547
+ "grad_norm": 0.5757254958152771,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.2617,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.008479067302596715,
554
+ "grad_norm": 0.626308798789978,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.1739,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.008590633977630881,
561
+ "grad_norm": 0.5778496265411377,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.2306,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.008702200652665049,
568
+ "grad_norm": 0.6246429085731506,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.2534,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.008813767327699217,
575
+ "grad_norm": 0.5858237147331238,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.0923,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.008925334002733383,
582
+ "grad_norm": 0.6260606646537781,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.1888,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.009036900677767551,
589
+ "grad_norm": 0.630234956741333,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.2772,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.009148467352801719,
596
+ "grad_norm": 0.6444050669670105,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.1496,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.009260034027835885,
603
+ "grad_norm": 0.6214231252670288,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.255,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.009371600702870053,
610
+ "grad_norm": 0.6371873021125793,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.362,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.00948316737790422,
617
+ "grad_norm": 0.652386486530304,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 1.257,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.009594734052938387,
624
+ "grad_norm": 0.6756475567817688,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.0734,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.009706300727972555,
631
+ "grad_norm": 0.6765338778495789,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.3687,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.009817867403006723,
638
+ "grad_norm": 0.6886449456214905,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.0611,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.009929434078040889,
645
+ "grad_norm": 0.7021864056587219,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.2352,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.010041000753075057,
652
+ "grad_norm": 0.7063576579093933,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.0392,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.010152567428109223,
659
+ "grad_norm": 0.6913172602653503,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.0881,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.01026413410314339,
666
+ "grad_norm": 0.8174880146980286,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.0368,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.010375700778177559,
673
+ "grad_norm": 0.7189077734947205,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 1.0234,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.010487267453211725,
680
+ "grad_norm": 0.7540398836135864,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 1.3022,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.010598834128245893,
687
+ "grad_norm": 0.7480753064155579,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.1476,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.01071040080328006,
694
+ "grad_norm": 0.7380363345146179,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 1.1075,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.010821967478314227,
701
+ "grad_norm": 0.7782248258590698,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 1.0968,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.010933534153348395,
708
+ "grad_norm": 0.8116884827613831,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 1.0562,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.011045100828382563,
715
+ "grad_norm": 0.8749708533287048,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 1.0236,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.011156667503416729,
722
+ "grad_norm": 0.9371297359466553,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.8881,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.011156667503416729,
729
+ "eval_loss": 1.2055939435958862,
730
+ "eval_runtime": 455.4273,
731
+ "eval_samples_per_second": 33.149,
732
+ "eval_steps_per_second": 8.289,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 2.796287107792896e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null