Hugging Face's logo

lesso03
/
98d3d7f5-bec2-44e1-a24b-ce2333b65fa4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso03 commited on
Commit
e01aba9
•
1 Parent(s): 3666fa7

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:bda064689ed5f85817e5a66c665112a2c0642e367e569ced7d25634e9a8f675b
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62c13a0f6c226f7d9b1d312ab87fa57cf33f48a9fd39eb23d23e3a59a6f32d8
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fdb0f04da5d995257ec5fef324dbb8f5d45a812aaf0166431dcd394df07a05c
3
  size 90365754
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99124b306918032c2cc01eb2d00ec5d79ea0f03308292f97feeb46811d489dae
3
  size 90365754
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:026030288cd601691b26a9dd3addc963d8372e0cdb3ae5ae397bb1e558a3e4d2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a797e4556a00e672702ff04c6ecce740fabaca58e7ff5b6ddf14351f843364
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": 0.001134301270417423,
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": 1.9938,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 4838612847820800.0,
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": 0.0017014519056261343,
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": 1.9938,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.0011569872958257714,
411
+ "grad_norm": 2.376706600189209,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 1.9896,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.0011796733212341198,
418
+ "grad_norm": 2.9564199447631836,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 2.014,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.0012023593466424683,
425
+ "grad_norm": 1.6720558404922485,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 2.0453,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.0012250453720508167,
432
+ "grad_norm": 1.6735769510269165,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.9324,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.0012250453720508167,
439
+ "eval_loss": 1.9686158895492554,
440
+ "eval_runtime": 1114.5532,
441
+ "eval_samples_per_second": 33.305,
442
+ "eval_steps_per_second": 4.163,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.0012477313974591652,
447
+ "grad_norm": 1.9759901762008667,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.97,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.0012704174228675136,
454
+ "grad_norm": 1.0385563373565674,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 2.0125,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.001293103448275862,
461
+ "grad_norm": 1.4511593580245972,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 1.9829,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.0013157894736842105,
468
+ "grad_norm": 1.8236950635910034,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 1.9339,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.001338475499092559,
475
+ "grad_norm": 1.1144325733184814,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.9466,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.0013611615245009074,
482
+ "grad_norm": 1.2293871641159058,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.9279,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.0013838475499092558,
489
+ "grad_norm": 1.463137149810791,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 1.9596,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.0014065335753176043,
496
+ "grad_norm": 1.4150505065917969,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.9864,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.0014292196007259527,
503
+ "grad_norm": 1.1374602317810059,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 1.9059,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.0014292196007259527,
510
+ "eval_loss": 1.9304600954055786,
511
+ "eval_runtime": 1115.0604,
512
+ "eval_samples_per_second": 33.29,
513
+ "eval_steps_per_second": 4.161,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.0014519056261343012,
518
+ "grad_norm": 1.5794055461883545,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 1.9551,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.0014745916515426498,
525
+ "grad_norm": 1.5883877277374268,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 1.9923,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.0014972776769509983,
532
+ "grad_norm": 1.667925477027893,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 1.9198,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.0015199637023593467,
539
+ "grad_norm": 1.3011813163757324,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.9227,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.0015426497277676952,
546
+ "grad_norm": 1.1233218908309937,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 1.9375,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.0015653357531760436,
553
+ "grad_norm": 1.5612938404083252,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.9055,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.001588021778584392,
560
+ "grad_norm": 1.4924774169921875,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.869,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.0016107078039927405,
567
+ "grad_norm": 2.727558135986328,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 1.9358,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.001633393829401089,
574
+ "grad_norm": 1.8907184600830078,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 1.9428,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.001633393829401089,
581
+ "eval_loss": 1.9025388956069946,
582
+ "eval_runtime": 1114.1295,
583
+ "eval_samples_per_second": 33.317,
584
+ "eval_steps_per_second": 4.165,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.0016560798548094374,
589
+ "grad_norm": 1.7879000902175903,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 1.9134,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.0016787658802177858,
596
+ "grad_norm": 3.1762635707855225,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.9674,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.0017014519056261343,
603
+ "grad_norm": 4.063128471374512,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 1.9046,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 7257919271731200.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null