Hugging Face's logo

lesso01
/
560c0c17-e48a-45a5-8973-3b038c39fe6c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
lesso01 commited on
Commit
8070c4b
•
1 Parent(s): 30da8b5

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:b24bbe774f0d17debed0b6849f76e217e797f9f1bf0a056b11ff44a7f42c5cb6
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e5c64f72918c5e267c96c1c6d9e79364d73dc15cea25431c37f4368ffc1ac4
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c266486906ca1441079e6ae5892f8c44ea161f03f0edfcebde86fe4fcc3b16a6
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b65d227dba14bcdd21e3c07fc30cd702ab28746377f13eca6105d768d2f58c83
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10b0f4f9d935debe1754d2bcdf6836577fd7f75677fdbebc826454f63e3fb737
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074e8690a8d61dba7a66649463fc8a03dc8e3c47ce5a5c77b759d178ed3f5ec7
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": 0.0011231033592021473,
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": 3.185,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 3.26729100951552e+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": 0.001684655038803221,
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": 3.185,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.0011455654263861903,
411
+ "grad_norm": 2.4340100288391113,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 3.9648,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.0011680274935702332,
418
+ "grad_norm": 2.181459903717041,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 3.8834,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.0011904895607542762,
425
+ "grad_norm": 1.8149747848510742,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 3.6703,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.0012129516279383193,
432
+ "grad_norm": 1.6692755222320557,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 3.6665,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.0012129516279383193,
439
+ "eval_loss": 1.7456862926483154,
440
+ "eval_runtime": 1632.4662,
441
+ "eval_samples_per_second": 22.965,
442
+ "eval_steps_per_second": 2.871,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.001235413695122362,
447
+ "grad_norm": 2.4753801822662354,
448
+ "learning_rate": 5e-05,
449
+ "loss": 3.4893,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.0012578757623064052,
454
+ "grad_norm": 2.4215543270111084,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 3.5557,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.001280337829490448,
461
+ "grad_norm": 2.677598476409912,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 2.9957,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.001302799896674491,
468
+ "grad_norm": 1.6023344993591309,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 4.1756,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.0013252619638585339,
475
+ "grad_norm": 1.8356449604034424,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 3.8109,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.001347724031042577,
482
+ "grad_norm": 1.8622589111328125,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 3.7408,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.0013701860982266198,
489
+ "grad_norm": 1.797446846961975,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 3.7321,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.0013926481654106628,
496
+ "grad_norm": 1.903319239616394,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 2.697,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.0014151102325947057,
503
+ "grad_norm": 1.7271318435668945,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 3.7319,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.0014151102325947057,
510
+ "eval_loss": 1.7400661706924438,
511
+ "eval_runtime": 1632.0443,
512
+ "eval_samples_per_second": 22.971,
513
+ "eval_steps_per_second": 2.872,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.0014375722997787487,
518
+ "grad_norm": 1.791338324546814,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 3.0344,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.0014600343669627916,
525
+ "grad_norm": 1.845373511314392,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 3.6643,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.0014824964341468346,
532
+ "grad_norm": 1.535976767539978,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 2.8485,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.0015049585013308775,
539
+ "grad_norm": 1.7403994798660278,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 3.1442,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.0015274205685149205,
546
+ "grad_norm": 1.6058380603790283,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 3.4109,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.0015498826356989633,
553
+ "grad_norm": 1.738742709159851,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 3.1998,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.0015723447028830064,
560
+ "grad_norm": 1.8473705053329468,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 3.399,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.0015948067700670492,
567
+ "grad_norm": 1.9509713649749756,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 3.4907,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.0016172688372510923,
574
+ "grad_norm": 1.8196882009506226,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 3.8142,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.0016172688372510923,
581
+ "eval_loss": 1.7379201650619507,
582
+ "eval_runtime": 1632.391,
583
+ "eval_samples_per_second": 22.966,
584
+ "eval_steps_per_second": 2.871,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.0016397309044351351,
589
+ "grad_norm": 1.8369139432907104,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 3.736,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.0016621929716191782,
596
+ "grad_norm": 1.637620210647583,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 3.7325,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.001684655038803221,
603
+ "grad_norm": 1.5396091938018799,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 3.349,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 4.90093651427328e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null