RoyJoy commited on
Commit
feb2381
1 Parent(s): 6be1eeb

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:c8272a38f3d535f54d6d85c84a949f07374e3a91c84ffaafcc64931c94a4a6ff
3
  size 100966336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a012c2820ba0237cc64680cf69e9d38ebfbed5a291b322a883ca90225048e22
3
  size 100966336
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:748fc115ffd337d3af3cf97001d7f98b863df002d47e2c4c8f815fe8934f6cef
3
  size 202110330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22bcc63d0ef26744cc14aa28d5fb394da8e5ae65fcbcb85b1dc16cb403704391
3
  size 202110330
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65248751b9d1f4974ce7e76e6708a0d1fc2e1229a1cb7754e108886031b99470
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5742dd433ee3ae60e4b3a90fdad43ff46cc6ea4b4f2744fa31781352ce7ddb2b
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 sha256:8690e916f94ab2f0cde1f3a30b694f44f07173f24b1c4640a41cc1561b73d277
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1c972811a5b35b45ca0f9da96ca5d4ccad8141bb4c6eedf8ef5c25d450faff
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 sha256:35a1d80028cd2421d5e6589956e5e261338acce94b00a3982a1856b50ab8c8dd
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb9c6b9c0c2d5452cfb6e67cd9803d35665084bb5eaec4c9434f39252459f5a
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 sha256:5b3ebe4c276db977fd509c8039e5b36d1c72fe7ee7627ec25f09160fb45458b2
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99006e2dcbe2a806a4e5201319fb8556cfc5e36b099db46ef1a3899ca6ff4a37
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.0427753925323486,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.626713670191931,
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": 99.253,
382
  "eval_steps_per_second": 25.806,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -409,7 +592,7 @@
409
  "attributes": {}
410
  }
411
  },
412
- "total_flos": 8.437038735740109e+16,
413
  "train_batch_size": 1,
414
  "trial_name": null,
415
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0223414897918701,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-75",
4
+ "epoch": 0.9400705052878966,
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": 99.253,
382
  "eval_steps_per_second": 25.806,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.6392479435957696,
387
+ "grad_norm": 0.6127623915672302,
388
+ "learning_rate": 5.7231268960295e-05,
389
+ "loss": 1.5449,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.6517822169996083,
394
+ "grad_norm": 0.15788757801055908,
395
+ "learning_rate": 5.574402751448614e-05,
396
+ "loss": 1.1523,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.664316490403447,
401
+ "grad_norm": 0.19719970226287842,
402
+ "learning_rate": 5.425597248551387e-05,
403
+ "loss": 1.0965,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.6768507638072856,
408
+ "grad_norm": 0.20220746099948883,
409
+ "learning_rate": 5.2768731039705e-05,
410
+ "loss": 1.0729,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.6893850372111242,
415
+ "grad_norm": 0.21883238852024078,
416
+ "learning_rate": 5.128392945374505e-05,
417
+ "loss": 1.0133,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.7019193106149628,
422
+ "grad_norm": 0.20048078894615173,
423
+ "learning_rate": 4.980319133636863e-05,
424
+ "loss": 0.9661,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.7144535840188014,
429
+ "grad_norm": 0.23357737064361572,
430
+ "learning_rate": 4.83281358529671e-05,
431
+ "loss": 0.983,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.72698785742264,
436
+ "grad_norm": 0.24839633703231812,
437
+ "learning_rate": 4.686037595505507e-05,
438
+ "loss": 1.0299,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.7395221308264787,
443
+ "grad_norm": 0.2856897711753845,
444
+ "learning_rate": 4.54015166165314e-05,
445
+ "loss": 1.083,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.7520564042303173,
450
+ "grad_norm": 0.3443909287452698,
451
+ "learning_rate": 4.395315307866405e-05,
452
+ "loss": 1.0942,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.7645906776341559,
457
+ "grad_norm": 0.3818349242210388,
458
+ "learning_rate": 4.2516869105717004e-05,
459
+ "loss": 1.1876,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.7771249510379945,
464
+ "grad_norm": 0.5584022998809814,
465
+ "learning_rate": 4.109423525312738e-05,
466
+ "loss": 1.2389,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.7896592244418331,
471
+ "grad_norm": 1.83659029006958,
472
+ "learning_rate": 3.968680715012606e-05,
473
+ "loss": 1.8469,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.8021934978456717,
478
+ "grad_norm": 0.15524441003799438,
479
+ "learning_rate": 3.829612379868006e-05,
480
+ "loss": 1.1955,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.8147277712495103,
485
+ "grad_norm": 0.15641632676124573,
486
+ "learning_rate": 3.692370589061639e-05,
487
+ "loss": 1.1487,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.827262044653349,
492
+ "grad_norm": 0.1683935523033142,
493
+ "learning_rate": 3.557105414476782e-05,
494
+ "loss": 1.0506,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.8397963180571876,
499
+ "grad_norm": 0.17298902571201324,
500
+ "learning_rate": 3.423964766595906e-05,
501
+ "loss": 1.0407,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.8523305914610263,
506
+ "grad_norm": 0.19782142341136932,
507
+ "learning_rate": 3.293094232762715e-05,
508
+ "loss": 0.9614,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.8648648648648649,
513
+ "grad_norm": 0.2152557373046875,
514
+ "learning_rate": 3.164636917984534e-05,
515
+ "loss": 0.9624,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.8773991382687035,
520
+ "grad_norm": 0.2377156764268875,
521
+ "learning_rate": 3.0387332884490805e-05,
522
+ "loss": 0.9853,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.8899334116725421,
527
+ "grad_norm": 0.24591700732707977,
528
+ "learning_rate": 2.9155210179267546e-05,
529
+ "loss": 1.0166,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.9024676850763808,
534
+ "grad_norm": 0.32400262355804443,
535
+ "learning_rate": 2.7951348372263875e-05,
536
+ "loss": 1.0993,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.9150019584802194,
541
+ "grad_norm": 0.3385933041572571,
542
+ "learning_rate": 2.677706386869083e-05,
543
+ "loss": 1.0851,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 0.927536231884058,
548
+ "grad_norm": 0.4308682382106781,
549
+ "learning_rate": 2.5633640731412412e-05,
550
+ "loss": 1.1932,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 0.9400705052878966,
555
+ "grad_norm": 0.8425101041793823,
556
+ "learning_rate": 2.4522329276841663e-05,
557
+ "loss": 1.2269,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 0.9400705052878966,
562
+ "eval_loss": 1.0223414897918701,
563
+ "eval_runtime": 0.5047,
564
+ "eval_samples_per_second": 99.066,
565
+ "eval_steps_per_second": 25.757,
566
+ "step": 75
567
  }
568
  ],
569
  "logging_steps": 1,
 
592
  "attributes": {}
593
  }
594
  },
595
+ "total_flos": 1.26601158625067e+17,
596
  "train_batch_size": 1,
597
  "trial_name": null,
598
  "trial_params": null