prxy5604 commited on
Commit
d9fc663
·
verified ·
1 Parent(s): 6c5bcc4

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:bc1dcf2303270be0bac04447dfa68a7a0b2a114fdf450e8ea485f684d1d7fa11
3
  size 121155320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8091146d86e73c43ca8c78869aaee902be0a94a81f8e73f23da8968d5dcd981e
3
  size 121155320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6108a2b2cd69b9d7281d0c56e405ef30006a8d097289a646588de92354ef536
3
  size 61896852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4156b381e561cbde84db857bb1e1bb2d2f893b67afd6809f0d6eb01ac2b0e9
3
  size 61896852
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a584b4ce41b239fa74e376fb5d59471ea59be6e018ae7dc86a221cd582f7eba2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba78ba071c3781f9b37ddc8c776bceecb359426253a6769caca3e23a281e8558
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": 1.554897427558899,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.2107481559536354,
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": 61.857,
374
  "eval_steps_per_second": 15.464,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -401,7 +759,7 @@
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 3329388183552000.0,
405
  "train_batch_size": 8,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.090325117111206,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.4214963119072708,
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": 61.857,
374
  "eval_steps_per_second": 15.464,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.21496311907270813,
379
+ "grad_norm": 4.251574516296387,
380
+ "learning_rate": 8.894386393810563e-05,
381
+ "loss": 2.1604,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.2191780821917808,
386
+ "grad_norm": 3.9960267543792725,
387
+ "learning_rate": 8.842005554284296e-05,
388
+ "loss": 2.0034,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.22339304531085352,
393
+ "grad_norm": 3.5435032844543457,
394
+ "learning_rate": 8.788574348801675e-05,
395
+ "loss": 2.1025,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.22760800842992623,
400
+ "grad_norm": 2.965231418609619,
401
+ "learning_rate": 8.73410738492077e-05,
402
+ "loss": 1.6474,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.23182297154899895,
407
+ "grad_norm": 2.7395787239074707,
408
+ "learning_rate": 8.678619553365659e-05,
409
+ "loss": 1.5813,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.23603793466807166,
414
+ "grad_norm": 3.470393657684326,
415
+ "learning_rate": 8.622126023955446e-05,
416
+ "loss": 1.8214,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.24025289778714437,
421
+ "grad_norm": 3.1501359939575195,
422
+ "learning_rate": 8.564642241456986e-05,
423
+ "loss": 1.604,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.24446786090621708,
428
+ "grad_norm": 3.092348337173462,
429
+ "learning_rate": 8.506183921362443e-05,
430
+ "loss": 1.6645,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.24868282402528977,
435
+ "grad_norm": 2.8015921115875244,
436
+ "learning_rate": 8.44676704559283e-05,
437
+ "loss": 1.6998,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.2528977871443625,
442
+ "grad_norm": 2.905069589614868,
443
+ "learning_rate": 8.386407858128706e-05,
444
+ "loss": 1.5711,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.2571127502634352,
449
+ "grad_norm": 2.585193634033203,
450
+ "learning_rate": 8.32512286056924e-05,
451
+ "loss": 1.3652,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.2613277133825079,
456
+ "grad_norm": 3.029945135116577,
457
+ "learning_rate": 8.262928807620843e-05,
458
+ "loss": 1.4766,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.2655426765015806,
463
+ "grad_norm": 2.936624050140381,
464
+ "learning_rate": 8.199842702516583e-05,
465
+ "loss": 1.4975,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.2697576396206533,
470
+ "grad_norm": 2.7380998134613037,
471
+ "learning_rate": 8.135881792367686e-05,
472
+ "loss": 1.4037,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.273972602739726,
477
+ "grad_norm": 2.9049437046051025,
478
+ "learning_rate": 8.07106356344834e-05,
479
+ "loss": 1.5488,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.2781875658587987,
484
+ "grad_norm": 2.983566999435425,
485
+ "learning_rate": 8.005405736415126e-05,
486
+ "loss": 1.3697,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.28240252897787144,
491
+ "grad_norm": 3.108199119567871,
492
+ "learning_rate": 7.938926261462366e-05,
493
+ "loss": 1.4842,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.28661749209694415,
498
+ "grad_norm": 2.9537482261657715,
499
+ "learning_rate": 7.871643313414718e-05,
500
+ "loss": 1.2233,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.29083245521601686,
505
+ "grad_norm": 3.0543484687805176,
506
+ "learning_rate": 7.803575286758364e-05,
507
+ "loss": 1.4292,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.2950474183350896,
512
+ "grad_norm": 3.0750956535339355,
513
+ "learning_rate": 7.734740790612136e-05,
514
+ "loss": 1.4593,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.2992623814541623,
519
+ "grad_norm": 3.2659246921539307,
520
+ "learning_rate": 7.66515864363997e-05,
521
+ "loss": 1.2492,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.303477344573235,
526
+ "grad_norm": 3.628136396408081,
527
+ "learning_rate": 7.594847868906076e-05,
528
+ "loss": 1.5088,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.3076923076923077,
533
+ "grad_norm": 3.5745816230773926,
534
+ "learning_rate": 7.52382768867422e-05,
535
+ "loss": 1.5352,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.3119072708113804,
540
+ "grad_norm": 2.7928030490875244,
541
+ "learning_rate": 7.452117519152542e-05,
542
+ "loss": 1.121,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.31612223393045313,
547
+ "grad_norm": 3.3540618419647217,
548
+ "learning_rate": 7.379736965185368e-05,
549
+ "loss": 1.2916,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.3203371970495258,
554
+ "grad_norm": 3.366863965988159,
555
+ "learning_rate": 7.30670581489344e-05,
556
+ "loss": 1.388,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.3245521601685985,
561
+ "grad_norm": 3.5833253860473633,
562
+ "learning_rate": 7.233044034264034e-05,
563
+ "loss": 1.4952,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.3287671232876712,
568
+ "grad_norm": 3.5157740116119385,
569
+ "learning_rate": 7.158771761692464e-05,
570
+ "loss": 1.1532,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.3329820864067439,
575
+ "grad_norm": 3.7377912998199463,
576
+ "learning_rate": 7.083909302476453e-05,
577
+ "loss": 1.3759,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.33719704952581664,
582
+ "grad_norm": 3.495645761489868,
583
+ "learning_rate": 7.008477123264848e-05,
584
+ "loss": 1.1822,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.34141201264488935,
589
+ "grad_norm": 3.4798645973205566,
590
+ "learning_rate": 6.932495846462261e-05,
591
+ "loss": 1.1689,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.34562697576396206,
596
+ "grad_norm": 3.490549087524414,
597
+ "learning_rate": 6.855986244591104e-05,
598
+ "loss": 1.3261,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.3498419388830348,
603
+ "grad_norm": 4.399184226989746,
604
+ "learning_rate": 6.778969234612584e-05,
605
+ "loss": 1.2789,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.3540569020021075,
610
+ "grad_norm": 3.5043818950653076,
611
+ "learning_rate": 6.701465872208216e-05,
612
+ "loss": 1.2317,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.3582718651211802,
617
+ "grad_norm": 3.1400296688079834,
618
+ "learning_rate": 6.623497346023418e-05,
619
+ "loss": 0.9662,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.3624868282402529,
624
+ "grad_norm": 3.659299612045288,
625
+ "learning_rate": 6.545084971874738e-05,
626
+ "loss": 1.1803,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.3667017913593256,
631
+ "grad_norm": 4.160400867462158,
632
+ "learning_rate": 6.466250186922325e-05,
633
+ "loss": 1.413,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.37091675447839834,
638
+ "grad_norm": 3.50260853767395,
639
+ "learning_rate": 6.387014543809223e-05,
640
+ "loss": 1.0956,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.37513171759747105,
645
+ "grad_norm": 3.959489345550537,
646
+ "learning_rate": 6.307399704769099e-05,
647
+ "loss": 1.2424,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.3793466807165437,
652
+ "grad_norm": 3.793694019317627,
653
+ "learning_rate": 6.227427435703997e-05,
654
+ "loss": 1.0903,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.3835616438356164,
659
+ "grad_norm": 3.3994905948638916,
660
+ "learning_rate": 6.147119600233758e-05,
661
+ "loss": 1.0591,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.38777660695468913,
666
+ "grad_norm": 3.680428981781006,
667
+ "learning_rate": 6.066498153718735e-05,
668
+ "loss": 1.0473,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.39199157007376184,
673
+ "grad_norm": 3.4609715938568115,
674
+ "learning_rate": 5.985585137257401e-05,
675
+ "loss": 0.8781,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.39620653319283455,
680
+ "grad_norm": 3.00770902633667,
681
+ "learning_rate": 5.90440267166055e-05,
682
+ "loss": 0.6652,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.40042149631190727,
687
+ "grad_norm": 4.031708240509033,
688
+ "learning_rate": 5.8229729514036705e-05,
689
+ "loss": 1.1705,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.40463645943098,
694
+ "grad_norm": 4.026821613311768,
695
+ "learning_rate": 5.74131823855921e-05,
696
+ "loss": 0.8865,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.4088514225500527,
701
+ "grad_norm": 3.490584373474121,
702
+ "learning_rate": 5.6594608567103456e-05,
703
+ "loss": 0.654,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.4130663856691254,
708
+ "grad_norm": 4.305174350738525,
709
+ "learning_rate": 5.577423184847932e-05,
710
+ "loss": 0.8525,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.4172813487881981,
715
+ "grad_norm": 3.9346580505371094,
716
+ "learning_rate": 5.495227651252315e-05,
717
+ "loss": 0.9059,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 0.4214963119072708,
722
+ "grad_norm": 4.256545066833496,
723
+ "learning_rate": 5.4128967273616625e-05,
724
+ "loss": 0.9487,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 0.4214963119072708,
729
+ "eval_loss": 1.090325117111206,
730
+ "eval_runtime": 6.446,
731
+ "eval_samples_per_second": 62.054,
732
+ "eval_steps_per_second": 15.513,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 6658776367104000.0,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null