Hugging Face's logo

lesso05
/
06703743-b448-4998-9385-0bc215f249b4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso05 commited on
Commit
d804ad3
·
verified ·
1 Parent(s): 7f9dde8

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:df9675b8b429fce62e6ff8894dc2719b406d92def43d2f5f750481a9e2154aa7
3
  size 767856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6cccfc9518afa0fdc33a7ea0aaaef064c976c628408a5a2b59dc210fc1c161
3
  size 767856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03cc383ddbb970086c33a92448b79eeee8dbf43723473d712f50eac130f9d91c
3
  size 1601338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54cfa3242ed178d00bf7e0e3fc3ec8ee0289f082799ba2db53b5fd90088d3dda
3
  size 1601338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:561c96a9de2039e2fc252d4f61038d8c0e79bafac8eb8ddb35ced95407e0d204
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d20bd7f9e98977739901deb4ac065306087d350d274dcb68e6b2fdb27bdb7adc
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": 0.009000900090009001,
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": 9.4796,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 13574760038400.0,
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": 0.013501350135013501,
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": 9.4796,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.009180918091809182,
411
+ "grad_norm": 5.1421217918396,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 9.5437,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.00936093609360936,
418
+ "grad_norm": 4.592971324920654,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 9.1944,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.00954095409540954,
425
+ "grad_norm": 5.622161865234375,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 9.6394,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.00972097209720972,
432
+ "grad_norm": 5.27858829498291,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 9.5195,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.00972097209720972,
439
+ "eval_loss": 9.32948112487793,
440
+ "eval_runtime": 41.5183,
441
+ "eval_samples_per_second": 112.673,
442
+ "eval_steps_per_second": 14.09,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.009900990099009901,
447
+ "grad_norm": 4.497775077819824,
448
+ "learning_rate": 5e-05,
449
+ "loss": 9.308,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.010081008100810081,
454
+ "grad_norm": 4.790937900543213,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 9.3374,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.010261026102610262,
461
+ "grad_norm": 4.156779766082764,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 9.0797,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.01044104410441044,
468
+ "grad_norm": 5.075934410095215,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 9.1865,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.01062106210621062,
475
+ "grad_norm": 5.212141513824463,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 9.2446,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.010801080108010801,
482
+ "grad_norm": 4.7454705238342285,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 9.1307,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.010981098109810981,
489
+ "grad_norm": 4.656852722167969,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 8.9722,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.011161116111611162,
496
+ "grad_norm": 4.986353397369385,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 9.6201,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.01134113411341134,
503
+ "grad_norm": 4.1770830154418945,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 9.1031,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.01134113411341134,
510
+ "eval_loss": 9.168355941772461,
511
+ "eval_runtime": 41.4788,
512
+ "eval_samples_per_second": 112.781,
513
+ "eval_steps_per_second": 14.104,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.01152115211521152,
518
+ "grad_norm": 5.309531211853027,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 9.3599,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.011701170117011701,
525
+ "grad_norm": 4.383259296417236,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 9.15,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.011881188118811881,
532
+ "grad_norm": 4.308704853057861,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 9.0913,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.012061206120612062,
539
+ "grad_norm": 4.408690929412842,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 9.3145,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.012241224122412242,
546
+ "grad_norm": 4.576683521270752,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 8.8956,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.01242124212421242,
553
+ "grad_norm": 4.590541839599609,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 9.1312,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.012601260126012601,
560
+ "grad_norm": 4.922686576843262,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 9.0805,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.012781278127812781,
567
+ "grad_norm": 4.215728759765625,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 9.2433,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.012961296129612962,
574
+ "grad_norm": 4.534681797027588,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 8.948,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.012961296129612962,
581
+ "eval_loss": 9.072084426879883,
582
+ "eval_runtime": 41.5005,
583
+ "eval_samples_per_second": 112.721,
584
+ "eval_steps_per_second": 14.096,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.013141314131413142,
589
+ "grad_norm": 4.945130348205566,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 9.4625,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.01332133213321332,
596
+ "grad_norm": 4.447700500488281,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 8.8096,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.013501350135013501,
603
+ "grad_norm": 4.476735591888428,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 8.8277,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 20362140057600.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null