Hugging Face's logo

lesso04
/
b8629905-7210-44a2-9216-6597e8b20a21

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso04 commited on
Commit
cc21aa4
·
verified ·
1 Parent(s): 3129495

Training in progress, step 75, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +202 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03211b8eacdfbc99056c84a095672d82a8c697fb9a16e1930cb356a61c0f32b5
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c1377fb4a5dd252aa404ea5c5b1200d84b54bcbb288507527b716b7cf25f7c
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b6794964d2b68db89ac3ceb9f3ea9cb0766bb3a5e47f887d5925f9c42e0cf6d
3
  size 101184122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0806d8f17fa4f9c46c2702445d12114c2904201a6de24706c45b8c31a81ff0f
3
  size 101184122
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11514b197853b462348465f3dc339beef02f4f254b0c41ac5a64915cdbed9ea0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1d644a4a39d949387b662bdefaee2232811c755c916d4547d1e6e803c86cf5
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": 0.042105263157894736,
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": 0.6475,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 5146843860172800.0,
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": 0.06315789473684211,
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": 0.6475,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.04294736842105263,
411
+ "grad_norm": 0.6151592135429382,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.6265,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.043789473684210524,
418
+ "grad_norm": 0.5425090193748474,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.6481,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.04463157894736842,
425
+ "grad_norm": 0.51148921251297,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.6227,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.04547368421052632,
432
+ "grad_norm": 0.49863481521606445,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.6397,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.04547368421052632,
439
+ "eval_loss": 0.6352894306182861,
440
+ "eval_runtime": 28.7122,
441
+ "eval_samples_per_second": 34.828,
442
+ "eval_steps_per_second": 4.354,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.04631578947368421,
447
+ "grad_norm": 0.7179785370826721,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.6644,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.04715789473684211,
454
+ "grad_norm": 0.6957202553749084,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.6482,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.048,
461
+ "grad_norm": 0.47261208295822144,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.637,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.048842105263157895,
468
+ "grad_norm": 0.9482942819595337,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.6306,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.04968421052631579,
475
+ "grad_norm": 0.42428135871887207,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.6208,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.05052631578947368,
482
+ "grad_norm": 0.2713795304298401,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.6347,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.05136842105263158,
489
+ "grad_norm": 0.5890096426010132,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.6379,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.05221052631578947,
496
+ "grad_norm": 0.6223120093345642,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.6292,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.053052631578947365,
503
+ "grad_norm": 0.47491008043289185,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.631,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.053052631578947365,
510
+ "eval_loss": 0.6267176270484924,
511
+ "eval_runtime": 28.6879,
512
+ "eval_samples_per_second": 34.858,
513
+ "eval_steps_per_second": 4.357,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.053894736842105266,
518
+ "grad_norm": 0.8451453447341919,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.6133,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.05473684210526316,
525
+ "grad_norm": 0.6316500306129456,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.6295,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.055578947368421054,
532
+ "grad_norm": 0.475432813167572,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.6283,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.05642105263157895,
539
+ "grad_norm": 0.4279637038707733,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.6353,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.05726315789473684,
546
+ "grad_norm": 0.39883410930633545,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.6273,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.058105263157894736,
553
+ "grad_norm": 0.4334561824798584,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.6238,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.05894736842105263,
560
+ "grad_norm": 0.3239782452583313,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.6227,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.059789473684210524,
567
+ "grad_norm": 0.46495527029037476,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.6244,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.06063157894736842,
574
+ "grad_norm": 0.3789292573928833,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.6284,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.06063157894736842,
581
+ "eval_loss": 0.6295309066772461,
582
+ "eval_runtime": 28.6861,
583
+ "eval_samples_per_second": 34.86,
584
+ "eval_steps_per_second": 4.358,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.06147368421052631,
589
+ "grad_norm": 0.2577737867832184,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.6167,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.06231578947368421,
596
+ "grad_norm": 0.4692973494529724,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.6137,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.06315789473684211,
603
+ "grad_norm": 0.28481587767601013,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.6147,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 7720265790259200.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null