Hugging Face's logo

lesso07
/
272ed706-05e0-4b49-823b-853d79309fc1

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso07 commited on
Commit
2cae489
·
verified ·
1 Parent(s): 9fed244

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:cbc78164d3c21e8fc9898d3790d000a704d81088fb1af623d2f22911df32cd8e
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf52c1cb72ef80ad3ad0bdee1c595c8497946fb3887ff3de78c54066c51d7683
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39570c8d1990b479f1a99160d1e4ae91a2a81a454266186d1619fe4a88f7c5a9
3
  size 101184122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55526d89c3aae561046db5549ad32b127d5bb590a8e40d7bf9697fc3ff481ad8
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": 0.004700573469963335,
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": 0.5814,
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": 0.007050860204945004,
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": 0.5814,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.004794584939362603,
411
+ "grad_norm": 1.1322435140609741,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 0.6718,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.004888596408761869,
418
+ "grad_norm": 0.7453857064247131,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 0.5561,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.004982607878161136,
425
+ "grad_norm": 0.928943932056427,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.5619,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.005076619347560402,
432
+ "grad_norm": 0.9922681450843811,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 0.5967,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.005076619347560402,
439
+ "eval_loss": 0.563852846622467,
440
+ "eval_runtime": 253.4318,
441
+ "eval_samples_per_second": 35.347,
442
+ "eval_steps_per_second": 4.419,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.005170630816959669,
447
+ "grad_norm": 0.7717866897583008,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.4669,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.005264642286358936,
454
+ "grad_norm": 0.9942904710769653,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 0.6044,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.005358653755758202,
461
+ "grad_norm": 0.8181668519973755,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.5087,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.005452665225157469,
468
+ "grad_norm": 0.8513317108154297,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.5598,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.005546676694556736,
475
+ "grad_norm": 0.7018467783927917,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.5638,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.005640688163956003,
482
+ "grad_norm": 0.938843309879303,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 0.5768,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.0057346996333552695,
489
+ "grad_norm": 0.9042795300483704,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.5493,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.005828711102754536,
496
+ "grad_norm": 0.6332735419273376,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 0.531,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.005922722572153803,
503
+ "grad_norm": 1.0177136659622192,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 0.5125,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.005922722572153803,
510
+ "eval_loss": 0.5256929397583008,
511
+ "eval_runtime": 252.2686,
512
+ "eval_samples_per_second": 35.51,
513
+ "eval_steps_per_second": 4.44,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.006016734041553069,
518
+ "grad_norm": 0.7307918667793274,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.4858,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.006110745510952336,
525
+ "grad_norm": 1.128337025642395,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.6508,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.0062047569803516025,
532
+ "grad_norm": 0.6984878182411194,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 0.5505,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.00629876844975087,
539
+ "grad_norm": 0.873836874961853,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 0.5086,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.0063927799191501366,
546
+ "grad_norm": 0.9610751867294312,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.5957,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.006486791388549403,
553
+ "grad_norm": 0.841046154499054,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 0.5448,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.00658080285794867,
560
+ "grad_norm": 0.7103133201599121,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 0.4729,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.006674814327347936,
567
+ "grad_norm": 0.8467883467674255,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.5291,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.006768825796747203,
574
+ "grad_norm": 0.8004826903343201,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 0.4299,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.006768825796747203,
581
+ "eval_loss": 0.4963763654232025,
582
+ "eval_runtime": 252.6181,
583
+ "eval_samples_per_second": 35.461,
584
+ "eval_steps_per_second": 4.434,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.0068628372661464696,
589
+ "grad_norm": 0.7845374941825867,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.4789,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.006956848735545736,
596
+ "grad_norm": 0.7107625007629395,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 0.4897,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.007050860204945004,
603
+ "grad_norm": 0.8745075464248657,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.461,
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