0x1202 commited on
Commit
08ac2b6
·
verified ·
1 Parent(s): 9ed71ba

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 sha256:48f6f3104ae0e3e9a21093b650fa7265e5fe3f814c6fc04faf91dc19f66d14e2
3
  size 134235712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:741cc54559e3e0c962980e1aa4b18f7ea7f55de5cc5a55568baf31391e6cd26f
3
  size 134235712
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:763e9117f143f98b2aa3fb988d56a8e9033bb75191278997e579740233f1051e
3
  size 68309690
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8f490eb2c5550654142236fabea1feb9daba400fb74751ad751ba68314c831
3
  size 68309690
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d9f5ecf725a63151fcdb69e491b0d11d66410063dda879ed3019d656a096503
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c3246e5dfb62d8ef994b34cda4852ae86797bfc60b4d3057fe6367f7fadd24
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": 1.9609556198120117,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.34305317324185247,
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": 73.017,
374
  "eval_steps_per_second": 18.403,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 9263318355148800.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.8372527360916138,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.6861063464837049,
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": 73.017,
374
  "eval_steps_per_second": 18.403,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.34991423670668953,
379
+ "grad_norm": 4.2829484939575195,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 7.0131,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.3567753001715266,
386
+ "grad_norm": 4.773698806762695,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 7.0616,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.36363636363636365,
393
+ "grad_norm": 4.639217376708984,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 7.2588,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.3704974271012007,
400
+ "grad_norm": 4.57711124420166,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 6.2915,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.37735849056603776,
407
+ "grad_norm": 4.3175950050354,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 6.62,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.38421955403087477,
414
+ "grad_norm": 4.927550792694092,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 6.8197,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.3910806174957118,
421
+ "grad_norm": 5.108540058135986,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 6.652,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.3979416809605489,
428
+ "grad_norm": 5.311190128326416,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 6.654,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.40480274442538594,
435
+ "grad_norm": 5.356717109680176,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 6.7666,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.411663807890223,
442
+ "grad_norm": 5.327913761138916,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 7.324,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.41852487135506006,
449
+ "grad_norm": 5.4165191650390625,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 6.7351,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.42538593481989706,
456
+ "grad_norm": 5.452204704284668,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 5.4856,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.4322469982847341,
463
+ "grad_norm": 5.71651029586792,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 6.9173,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.4391080617495712,
470
+ "grad_norm": 6.328149318695068,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 7.5935,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.44596912521440824,
477
+ "grad_norm": 6.928874969482422,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 7.5651,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.4528301886792453,
484
+ "grad_norm": 6.131435394287109,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 6.1422,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.45969125214408235,
491
+ "grad_norm": 7.036497592926025,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 8.1299,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.4665523156089194,
498
+ "grad_norm": 7.607172966003418,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 7.5372,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.4734133790737564,
505
+ "grad_norm": 7.075242042541504,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 7.735,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.48027444253859347,
512
+ "grad_norm": 8.967554092407227,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 8.3584,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.48713550600343053,
519
+ "grad_norm": 10.635770797729492,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 7.8883,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.4939965694682676,
526
+ "grad_norm": 36.83614730834961,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 13.816,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.5008576329331046,
533
+ "grad_norm": 5.224258899688721,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 7.5155,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.5077186963979416,
540
+ "grad_norm": 5.5043864250183105,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 7.4326,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.5145797598627787,
547
+ "grad_norm": 4.99073600769043,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 7.7991,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.5214408233276158,
554
+ "grad_norm": 4.494393825531006,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 6.8002,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.5283018867924528,
561
+ "grad_norm": 4.096364974975586,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 6.5461,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.5351629502572899,
568
+ "grad_norm": 3.8724262714385986,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 7.0417,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.5420240137221269,
575
+ "grad_norm": 3.8217287063598633,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 6.084,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.548885077186964,
582
+ "grad_norm": 3.9765660762786865,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 6.8385,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.5557461406518011,
589
+ "grad_norm": 3.7557239532470703,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 5.9077,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.5626072041166381,
596
+ "grad_norm": 4.217108249664307,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 7.4603,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.5694682675814752,
603
+ "grad_norm": 3.938063144683838,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 6.4279,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.5763293310463122,
610
+ "grad_norm": 4.099449634552002,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 6.6643,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.5831903945111492,
617
+ "grad_norm": 4.268118381500244,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 7.2316,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.5900514579759862,
624
+ "grad_norm": 4.3306565284729,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 6.6102,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.5969125214408233,
631
+ "grad_norm": 4.440483570098877,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 6.7896,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.6037735849056604,
638
+ "grad_norm": 4.6268110275268555,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 6.8771,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.6106346483704974,
645
+ "grad_norm": 4.460641384124756,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 6.5277,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.6174957118353345,
652
+ "grad_norm": 4.795734405517578,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 7.0335,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.6243567753001715,
659
+ "grad_norm": 4.73524808883667,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 7.2792,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.6312178387650086,
666
+ "grad_norm": 4.746474742889404,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 6.5431,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.6380789022298456,
673
+ "grad_norm": 4.961014747619629,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 6.9168,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.6449399656946827,
680
+ "grad_norm": 5.02461051940918,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 6.2909,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.6518010291595198,
687
+ "grad_norm": 5.03878927230835,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 7.0238,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.6586620926243568,
694
+ "grad_norm": 5.197082996368408,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 6.0466,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.6655231560891939,
701
+ "grad_norm": 5.540366172790527,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 6.8652,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.6723842195540308,
708
+ "grad_norm": 5.839454650878906,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 6.4574,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.6792452830188679,
715
+ "grad_norm": 5.818624973297119,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 6.6828,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.6861063464837049,
722
+ "grad_norm": 5.735467433929443,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 7.0153,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.6861063464837049,
729
+ "eval_loss": 1.8372527360916138,
730
+ "eval_runtime": 3.3857,
731
+ "eval_samples_per_second": 72.659,
732
+ "eval_steps_per_second": 18.313,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 1.85266367102976e+16,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null