dada22231 commited on
Commit
02c8c52
·
verified ·
1 Parent(s): 73e2881

Training in progress, step 75, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3debc6cd130eb2243a4c132a1a7d7cf022648308f2ae1bb66dfbe48b4088b99e
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece3e019ea144b37c4c68435d1bee2ba711664d5c7ddf473f9642bfc9c6be565
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7fa76a3c5671e8eb6ec2baa556b0846978ed249edb3a11d204555d4702e55ce
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88bd3539bf03a90efed334ecc5074b7b3b090ac1537dd716bdaa33e9c3a0ccc6
3
  size 640009682
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13c87654199b0fb50f3f7332b8ec7a348a98e08641ae59bfea79dd82e50e251c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37df7a511c83cd4a782cbebdb12cf6b8b24ce2790bf7f37a999dd05ca188680
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8fabcb7916b68756e5caa4258f2b5132d082ee05c05bd062a246bbe1a73ed14
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf393e36d953418b100b43e644607133537d92333857bd362750595c77a0cef
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d532212ec3c2c2cca22fa25df2d7ee1478e88fbb99647a3268fe5d9cbb3b0496
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fac85b6f1b63e0c2a60fa71c36e0db2a0cfe635916e64bc82b7979136467e3b
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f3a37913969eb5b5a43defbcc383564bd8b39f52bcaa397ffaaaebe2a513967
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bce58b25d4dc8cd16eb072f714b64581288c0af3154bc744ec90bb6446165365
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.4655110836029053,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.8213552361396304,
5
  "eval_steps": 25,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -381,6 +381,189 @@
381
  "eval_samples_per_second": 8.681,
382
  "eval_steps_per_second": 2.257,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -404,12 +587,12 @@
404
  "should_evaluate": false,
405
  "should_log": false,
406
  "should_save": true,
407
- "should_training_stop": false
408
  },
409
  "attributes": {}
410
  }
411
  },
412
- "total_flos": 5.259156315439104e+17,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.42008838057518005,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-75",
4
+ "epoch": 1.2397330595482545,
5
  "eval_steps": 25,
6
+ "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
381
  "eval_samples_per_second": 8.681,
382
  "eval_steps_per_second": 2.257,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.837782340862423,
387
+ "grad_norm": 5.659170150756836,
388
+ "learning_rate": 3.250000000000001e-05,
389
+ "loss": 11.1576,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.8542094455852156,
394
+ "grad_norm": 6.056707859039307,
395
+ "learning_rate": 3.082151762439293e-05,
396
+ "loss": 12.4416,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.8706365503080082,
401
+ "grad_norm": 7.504565715789795,
402
+ "learning_rate": 2.9189060364202943e-05,
403
+ "loss": 12.7843,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.8870636550308009,
408
+ "grad_norm": 7.405429363250732,
409
+ "learning_rate": 2.760573569460757e-05,
410
+ "loss": 11.0891,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.9034907597535934,
415
+ "grad_norm": 7.66730260848999,
416
+ "learning_rate": 2.6074557564105727e-05,
417
+ "loss": 13.3666,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.919917864476386,
422
+ "grad_norm": 7.887065887451172,
423
+ "learning_rate": 2.459844065729529e-05,
424
+ "loss": 13.2792,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.9363449691991786,
429
+ "grad_norm": 9.200793266296387,
430
+ "learning_rate": 2.3180194846605367e-05,
431
+ "loss": 13.3564,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.9527720739219713,
436
+ "grad_norm": 10.53663158416748,
437
+ "learning_rate": 2.1822519843544424e-05,
438
+ "loss": 13.8408,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.9691991786447639,
443
+ "grad_norm": 13.007883071899414,
444
+ "learning_rate": 2.0528000059645997e-05,
445
+ "loss": 15.2171,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.9856262833675564,
450
+ "grad_norm": 13.825766563415527,
451
+ "learning_rate": 1.9299099686894423e-05,
452
+ "loss": 14.4066,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 1.0097535934291582,
457
+ "grad_norm": 9.631000518798828,
458
+ "learning_rate": 1.8138158006995364e-05,
459
+ "loss": 14.0623,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 1.0261806981519508,
464
+ "grad_norm": 5.951600551605225,
465
+ "learning_rate": 1.7047384938420154e-05,
466
+ "loss": 11.5878,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 1.0426078028747434,
471
+ "grad_norm": 7.176366329193115,
472
+ "learning_rate": 1.602885682970026e-05,
473
+ "loss": 11.9891,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 1.0590349075975358,
478
+ "grad_norm": 7.551855564117432,
479
+ "learning_rate": 1.5084512506980026e-05,
480
+ "loss": 11.8857,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 1.0754620123203285,
485
+ "grad_norm": 7.072691440582275,
486
+ "learning_rate": 1.4216149583350754e-05,
487
+ "loss": 10.2248,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 1.091889117043121,
492
+ "grad_norm": 7.221491813659668,
493
+ "learning_rate": 1.3425421036992098e-05,
494
+ "loss": 12.6456,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 1.1083162217659137,
499
+ "grad_norm": 9.254717826843262,
500
+ "learning_rate": 1.2713832064634126e-05,
501
+ "loss": 13.2907,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 1.1247433264887063,
506
+ "grad_norm": 10.752814292907715,
507
+ "learning_rate": 1.2082737216329794e-05,
508
+ "loss": 11.7131,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 1.141170431211499,
513
+ "grad_norm": 11.052801132202148,
514
+ "learning_rate": 1.1533337816991932e-05,
515
+ "loss": 12.7111,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 1.1575975359342916,
520
+ "grad_norm": 11.566272735595703,
521
+ "learning_rate": 1.1066679679603e-05,
522
+ "loss": 12.2675,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 1.1740246406570842,
527
+ "grad_norm": 12.651549339294434,
528
+ "learning_rate": 1.0683651114450641e-05,
529
+ "loss": 13.584,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 1.1904517453798769,
534
+ "grad_norm": 16.129188537597656,
535
+ "learning_rate": 1.0384981238178534e-05,
536
+ "loss": 13.3956,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 1.2068788501026695,
541
+ "grad_norm": 15.546525955200195,
542
+ "learning_rate": 1.017123858587145e-05,
543
+ "loss": 12.5153,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 1.2233059548254621,
548
+ "grad_norm": 6.207511901855469,
549
+ "learning_rate": 1.00428300288164e-05,
550
+ "loss": 10.1893,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 1.2397330595482545,
555
+ "grad_norm": 7.4357805252075195,
556
+ "learning_rate": 1e-05,
557
+ "loss": 11.033,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 1.2397330595482545,
562
+ "eval_loss": 0.42008838057518005,
563
+ "eval_runtime": 5.6982,
564
+ "eval_samples_per_second": 8.775,
565
+ "eval_steps_per_second": 2.281,
566
+ "step": 75
567
  }
568
  ],
569
  "logging_steps": 1,
 
587
  "should_evaluate": false,
588
  "should_log": false,
589
  "should_save": true,
590
+ "should_training_stop": true
591
  },
592
  "attributes": {}
593
  }
594
  },
595
+ "total_flos": 7.888734473158656e+17,
596
  "train_batch_size": 1,
597
  "trial_name": null,
598
  "trial_params": null