Hugging Face's logo

lesso06
/
b7e2f000-7633-42e3-80ee-2cae3f8d97a9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
lesso06 commited on
Commit
472db06
•
1 Parent(s): 9ea0fb0

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 sha256:6adfe329f21cb2b6ee7a247e6e2cd9d8cbbf1d924714e24318722e54d871f371
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e00262fed0eeed878ece671c0885e8d6bc3f98d981f69baedb78d4a47c8dcb
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8289d44338e341bb7cc973d90e7ba5dc97cf48adfc97f2262c0b86f66fb23105
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44ca007e6058e2aeeb280cad035dddd3aee30db465160559d6ddb42d0b198c54
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fb53a88c7f354580801381bf9f9cb68ea799947ddde7ac68dff170181f21647
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb641ed1c277039af8b8ba2d9d53cbbb8c158dbe992dc8c6e1ce8826e06e00b0
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": 0.0049808238282611945,
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": 1.6567,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 6.411308261965824e+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": 0.007471235742391792,
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": 1.6567,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.005080440304826418,
411
+ "grad_norm": 0.8188619017601013,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 1.6396,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.005180056781391642,
418
+ "grad_norm": 0.79249507188797,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 1.5557,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.005279673257956866,
425
+ "grad_norm": 0.6785992383956909,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 1.3073,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.00537928973452209,
432
+ "grad_norm": 0.97710782289505,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.7284,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.00537928973452209,
439
+ "eval_loss": 0.7754528522491455,
440
+ "eval_runtime": 1981.7331,
441
+ "eval_samples_per_second": 4.266,
442
+ "eval_steps_per_second": 0.533,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.005478906211087314,
447
+ "grad_norm": 0.6769554615020752,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.4189,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.005578522687652538,
454
+ "grad_norm": 0.7661912441253662,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.7372,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.005678139164217761,
461
+ "grad_norm": 0.6592562794685364,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 1.4502,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.005777755640782986,
468
+ "grad_norm": 0.7503229975700378,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 1.7161,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.00587737211734821,
475
+ "grad_norm": 0.732617974281311,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.7657,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.005976988593913433,
482
+ "grad_norm": 1.082809329032898,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.6904,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.006076605070478657,
489
+ "grad_norm": 0.7891655564308167,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 1.44,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.006176221547043881,
496
+ "grad_norm": 0.6875162124633789,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.4152,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.006275838023609105,
503
+ "grad_norm": 0.9231224656105042,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 1.5762,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.006275838023609105,
510
+ "eval_loss": 0.770641028881073,
511
+ "eval_runtime": 1982.7582,
512
+ "eval_samples_per_second": 4.264,
513
+ "eval_steps_per_second": 0.533,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.006375454500174329,
518
+ "grad_norm": 0.7868038415908813,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 1.5909,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.006475070976739552,
525
+ "grad_norm": 0.7078908681869507,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 1.3516,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.006574687453304777,
532
+ "grad_norm": 0.6930572986602783,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 1.4509,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.006674303929870001,
539
+ "grad_norm": 0.8317136764526367,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.7793,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.006773920406435224,
546
+ "grad_norm": 0.8354675769805908,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 1.7312,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.006873536883000448,
553
+ "grad_norm": 0.7719464302062988,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.8397,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.0069731533595656725,
560
+ "grad_norm": 0.7388513088226318,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.5045,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.007072769836130896,
567
+ "grad_norm": 0.8662011623382568,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 1.8403,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.00717238631269612,
574
+ "grad_norm": 0.9247857332229614,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 1.6341,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.00717238631269612,
581
+ "eval_loss": 0.7679572105407715,
582
+ "eval_runtime": 1983.463,
583
+ "eval_samples_per_second": 4.262,
584
+ "eval_steps_per_second": 0.533,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.007272002789261343,
589
+ "grad_norm": 0.6822766661643982,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 1.341,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.007371619265826568,
596
+ "grad_norm": 0.8702826499938965,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.6741,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.007471235742391792,
603
+ "grad_norm": 0.6422632932662964,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 1.3527,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 9.648701542760448e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null