lesso06 commited on
Commit
7fec00d
1 Parent(s): 0681dd9

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 sha256:98b09ed1e9c13e49669afe0d8bd92330ff66bcf02cab200f8cdbba070055a0b4
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e3ea2ceae1e1612375d36c5d9c3801dc8b8835f84585ccc46428284a3aa3b45
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17b57eb6333716efa0618af516d66c4ad8008a01ac362c7ecdfecdf8a39fc82b
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b3d30a0fa9db66eb32d2138c86e81afe558b2f5ec2cfa6587c2c8e1b660f81
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cad57760029cf28563e59df0d6afdcc3b95ff86cb77fe0cab8e460b3d873d363
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58b155e5123c7f1976665fc15d0993b62f2994fac0848287641211bae5ae5bc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.10638297872340426,
5
  "eval_steps": 9,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -405,6 +405,205 @@
405
  "learning_rate": 5.868240888334653e-05,
406
  "loss": 0.0537,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 6.53464644354048e+16,
428
  "train_batch_size": 8,
429
  "trial_name": null,
430
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1595744680851064,
5
  "eval_steps": 9,
6
+ "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
405
  "learning_rate": 5.868240888334653e-05,
406
  "loss": 0.0537,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.10851063829787234,
411
+ "grad_norm": 0.24473926424980164,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.1363,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.11063829787234042,
418
+ "grad_norm": 0.23498021066188812,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.0853,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.1127659574468085,
425
+ "grad_norm": 0.2749404013156891,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.0979,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.1148936170212766,
432
+ "grad_norm": 0.18543550372123718,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.0393,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.1148936170212766,
439
+ "eval_loss": 0.0312594510614872,
440
+ "eval_runtime": 137.3683,
441
+ "eval_samples_per_second": 2.883,
442
+ "eval_steps_per_second": 0.364,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.11702127659574468,
447
+ "grad_norm": 0.2447483092546463,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.0567,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.11914893617021277,
454
+ "grad_norm": 0.32978394627571106,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.018,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.12127659574468085,
461
+ "grad_norm": 0.19853627681732178,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.0312,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.12340425531914893,
468
+ "grad_norm": 0.17412202060222626,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.0432,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.125531914893617,
475
+ "grad_norm": 0.12538942694664001,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.02,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.1276595744680851,
482
+ "grad_norm": 0.184116929769516,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.0261,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.12978723404255318,
489
+ "grad_norm": 0.20825651288032532,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.0487,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.13191489361702127,
496
+ "grad_norm": 0.23447850346565247,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.0424,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.13404255319148936,
503
+ "grad_norm": 0.3336513340473175,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.0973,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.13404255319148936,
510
+ "eval_loss": 0.02362966351211071,
511
+ "eval_runtime": 137.1904,
512
+ "eval_samples_per_second": 2.886,
513
+ "eval_steps_per_second": 0.364,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.13617021276595745,
518
+ "grad_norm": 0.18834097683429718,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.0442,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.13829787234042554,
525
+ "grad_norm": 0.11435489356517792,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.0251,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.14042553191489363,
532
+ "grad_norm": 0.16500040888786316,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.0479,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.1425531914893617,
539
+ "grad_norm": 0.18839475512504578,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.05,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.14468085106382977,
546
+ "grad_norm": 0.18193626403808594,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.027,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.14680851063829786,
553
+ "grad_norm": 0.2267770916223526,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.0946,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.14893617021276595,
560
+ "grad_norm": 0.1924557089805603,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.0699,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.15106382978723404,
567
+ "grad_norm": 0.14939941465854645,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.0233,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.15319148936170213,
574
+ "grad_norm": 0.1674216091632843,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.0439,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.15319148936170213,
581
+ "eval_loss": 0.018976736813783646,
582
+ "eval_runtime": 137.2066,
583
+ "eval_samples_per_second": 2.886,
584
+ "eval_steps_per_second": 0.364,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.15531914893617021,
589
+ "grad_norm": 0.16422490775585175,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.0626,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.1574468085106383,
596
+ "grad_norm": 0.16370365023612976,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.0269,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.1595744680851064,
603
+ "grad_norm": 0.18531498312950134,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.0403,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 9.80196966531072e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null