Hugging Face's logo

lesso01
/
75b95d89-b151-48be-a820-8ce350cf252d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso01 commited on
Commit
8cb399a
·
verified ·
1 Parent(s): 913340e

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:a6ace4c0fb7c26c31e07805db0b130942f0c582543457ea0eff58053d9aec348
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0bcc31e44f150a98cb1a997e77bb0205a5d4a65d3e60071ecf7f651ab9ce3e2
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61ed248f858e1acffa463f69668f6a2ac4ba958d0e63319b2f45343241c34f2c
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7fa12d3dd4de9bd6e9a3bc7e35ddc9503239d30717fb2b16345b5b5d34ef741
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
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": 0.0027397260273972603,
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": 10.3679,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 5047186096128.0,
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": 0.00410958904109589,
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": 10.3679,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.0027945205479452057,
411
+ "grad_norm": 0.09698247164487839,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 10.366,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.0028493150684931507,
418
+ "grad_norm": 0.09390789270401001,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 10.3683,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.002904109589041096,
425
+ "grad_norm": 0.09476731717586517,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 10.3671,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.002958904109589041,
432
+ "grad_norm": 0.08774256706237793,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 10.3669,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.002958904109589041,
439
+ "eval_loss": 10.366765022277832,
440
+ "eval_runtime": 60.4002,
441
+ "eval_samples_per_second": 254.453,
442
+ "eval_steps_per_second": 31.821,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.0030136986301369864,
447
+ "grad_norm": 0.07979276031255722,
448
+ "learning_rate": 5e-05,
449
+ "loss": 10.3673,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.0030684931506849314,
454
+ "grad_norm": 0.08776028454303741,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 10.3688,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.0031232876712328768,
461
+ "grad_norm": 0.10283602774143219,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 10.3634,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.0031780821917808217,
468
+ "grad_norm": 0.08885012567043304,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 10.3652,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.003232876712328767,
475
+ "grad_norm": 0.1038474515080452,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 10.3662,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.0032876712328767125,
482
+ "grad_norm": 0.1030832901597023,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 10.3698,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.0033424657534246575,
489
+ "grad_norm": 0.10480338335037231,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 10.3614,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.003397260273972603,
496
+ "grad_norm": 0.10068631917238235,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 10.3642,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.003452054794520548,
503
+ "grad_norm": 0.09888831526041031,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 10.3679,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.003452054794520548,
510
+ "eval_loss": 10.36538028717041,
511
+ "eval_runtime": 60.2861,
512
+ "eval_samples_per_second": 254.934,
513
+ "eval_steps_per_second": 31.881,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.0035068493150684932,
518
+ "grad_norm": 0.09311617910861969,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 10.3667,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.003561643835616438,
525
+ "grad_norm": 0.09210352599620819,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 10.3646,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.0036164383561643836,
532
+ "grad_norm": 0.1097283810377121,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 10.3663,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.0036712328767123286,
539
+ "grad_norm": 0.09896838665008545,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 10.3631,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.003726027397260274,
546
+ "grad_norm": 0.09961827844381332,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 10.3652,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.0037808219178082194,
553
+ "grad_norm": 0.10928770154714584,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 10.3654,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.0038356164383561643,
560
+ "grad_norm": 0.09602166712284088,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 10.3624,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.0038904109589041097,
567
+ "grad_norm": 0.12611092627048492,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 10.3657,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.003945205479452055,
574
+ "grad_norm": 0.0977480337023735,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 10.3696,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.003945205479452055,
581
+ "eval_loss": 10.36441421508789,
582
+ "eval_runtime": 60.3533,
583
+ "eval_samples_per_second": 254.651,
584
+ "eval_steps_per_second": 31.846,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.004,
589
+ "grad_norm": 0.09957021474838257,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 10.3632,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.0040547945205479455,
596
+ "grad_norm": 0.10564438998699188,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 10.3663,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.00410958904109589,
603
+ "grad_norm": 0.1226331815123558,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 10.363,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 7636157202432.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null