Hugging Face's logo

fedovtt
/
1fdc103a-02d2-40bf-a6bc-1673fa607c0e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
fedovtt commited on
Commit
0372e10
·
verified ·
1 Parent(s): 7d19cfa

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 +187 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e128a7edfa271a43ffc8c41ddd0f4cfd32a9ac9e4c27646b9c012155190eb3d
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb75aa9dcca2b2b415ad98e99a82602b2a7d94f5a2d465e084fb0ecbad57cd97
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e4b2bc23ae01039b99d48aac443ead16ed5a346948baebe98718d3b00235213
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fba3997bf655e58038ab651a8dfe4718315f5161151e75b02128c0ad9b495fe
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef4f0148473100f8de623d21a2f3a77049b961024f4e3e11ffc26313622990b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f22db141f524238ddd18f27332b6688fc686788a2b628ad4b0e44082e23b0a7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
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": 0.1503194287861706,
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": 5.917,
382
  "eval_steps_per_second": 2.969,
383
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
384
  }
385
  ],
386
  "logging_steps": 1,
@@ -395,12 +578,12 @@
395
  "should_evaluate": false,
396
  "should_log": false,
397
  "should_save": true,
398
- "should_training_stop": false
399
  },
400
  "attributes": {}
401
  }
402
  },
403
- "total_flos": 7.49740504425431e+16,
404
  "train_batch_size": 2,
405
  "trial_name": null,
406
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.2254791431792559,
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": 5.917,
382
  "eval_steps_per_second": 2.969,
383
  "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.15332581736189402,
387
+ "grad_norm": 0.9507181644439697,
388
+ "learning_rate": 2.500000000000001e-05,
389
+ "loss": 0.7042,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.15633220593761743,
394
+ "grad_norm": 0.658510148525238,
395
+ "learning_rate": 2.3135019582658802e-05,
396
+ "loss": 0.8401,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.15933859451334084,
401
+ "grad_norm": 0.5643749237060547,
402
+ "learning_rate": 2.132117818244771e-05,
403
+ "loss": 0.8422,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.16234498308906425,
408
+ "grad_norm": 0.6225967407226562,
409
+ "learning_rate": 1.9561928549563968e-05,
410
+ "loss": 0.9282,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.16535137166478767,
415
+ "grad_norm": 0.6036686897277832,
416
+ "learning_rate": 1.7860619515673033e-05,
417
+ "loss": 0.9564,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.16835776024051108,
422
+ "grad_norm": 0.6316192150115967,
423
+ "learning_rate": 1.622048961921699e-05,
424
+ "loss": 0.8961,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.1713641488162345,
429
+ "grad_norm": 0.5374001860618591,
430
+ "learning_rate": 1.4644660940672627e-05,
431
+ "loss": 1.0148,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.1743705373919579,
436
+ "grad_norm": 0.4990711808204651,
437
+ "learning_rate": 1.3136133159493802e-05,
438
+ "loss": 0.9999,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.17737692596768131,
443
+ "grad_norm": 0.5350558161735535,
444
+ "learning_rate": 1.1697777844051105e-05,
445
+ "loss": 1.0145,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.18038331454340473,
450
+ "grad_norm": 0.5045204758644104,
451
+ "learning_rate": 1.0332332985438248e-05,
452
+ "loss": 1.0433,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.18338970311912814,
457
+ "grad_norm": 0.4548822045326233,
458
+ "learning_rate": 9.042397785550405e-06,
459
+ "loss": 0.9267,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.18639609169485155,
464
+ "grad_norm": 0.45933160185813904,
465
+ "learning_rate": 7.830427709355725e-06,
466
+ "loss": 1.0041,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.18940248027057496,
471
+ "grad_norm": 0.43838825821876526,
472
+ "learning_rate": 6.698729810778065e-06,
473
+ "loss": 0.9945,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.19240886884629838,
478
+ "grad_norm": 0.4817960858345032,
479
+ "learning_rate": 5.649458341088915e-06,
480
+ "loss": 1.0965,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.1954152574220218,
485
+ "grad_norm": 0.45825958251953125,
486
+ "learning_rate": 4.684610648167503e-06,
487
+ "loss": 1.1033,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.1984216459977452,
492
+ "grad_norm": 0.45766761898994446,
493
+ "learning_rate": 3.8060233744356633e-06,
494
+ "loss": 1.1072,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.2014280345734686,
499
+ "grad_norm": 0.45261964201927185,
500
+ "learning_rate": 3.0153689607045845e-06,
501
+ "loss": 1.0938,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.20443442314919202,
506
+ "grad_norm": 0.5117123126983643,
507
+ "learning_rate": 2.314152462588659e-06,
508
+ "loss": 1.1579,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.20744081172491544,
513
+ "grad_norm": 0.5163789987564087,
514
+ "learning_rate": 1.70370868554659e-06,
515
+ "loss": 1.0381,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.21044720030063885,
520
+ "grad_norm": 0.4221733510494232,
521
+ "learning_rate": 1.1851996440033319e-06,
522
+ "loss": 1.134,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.21345358887636226,
527
+ "grad_norm": 0.49074891209602356,
528
+ "learning_rate": 7.596123493895991e-07,
529
+ "loss": 1.1135,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.21645997745208567,
534
+ "grad_norm": 0.47700777649879456,
535
+ "learning_rate": 4.277569313094809e-07,
536
+ "loss": 1.2089,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.21946636602780908,
541
+ "grad_norm": 0.4848674237728119,
542
+ "learning_rate": 1.9026509541272275e-07,
543
+ "loss": 1.0768,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 0.2224727546035325,
548
+ "grad_norm": 0.4941892623901367,
549
+ "learning_rate": 4.7588920907110094e-08,
550
+ "loss": 1.048,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 0.2254791431792559,
555
+ "grad_norm": 0.49197641015052795,
556
+ "learning_rate": 0.0,
557
+ "loss": 1.1608,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 0.2254791431792559,
562
+ "eval_loss": 1.0857983827590942,
563
+ "eval_runtime": 47.8809,
564
+ "eval_samples_per_second": 5.869,
565
+ "eval_steps_per_second": 2.945,
566
+ "step": 75
567
  }
568
  ],
569
  "logging_steps": 1,
 
578
  "should_evaluate": false,
579
  "should_log": false,
580
  "should_save": true,
581
+ "should_training_stop": true
582
  },
583
  "attributes": {}
584
  }
585
  },
586
+ "total_flos": 1.1283408088989696e+17,
587
  "train_batch_size": 2,
588
  "trial_name": null,
589
  "trial_params": null