Hugging Face's logo

lesso01
/
cdfb3014-4a79-43f8-bfac-dfd281d98e5a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
lesso01 commited on
Commit
7f37e74
•
1 Parent(s): 27ba850

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:ce4af7a85f81eddebfd61247d3005446d1a1dc704565ff25800017436a77c518
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a287676bbd6f56d37f538890e248a985709aec41e5ac8693e31707472bf73c8
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9efff3c64a4e3205e3781def76b580a1382c230a6c26d77e33668dc1e0b6b59
3
  size 101184122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34529dce16c4845c072ff791f693d7dd4e45b301779591a7e33a893eb9958053
3
  size 101184122
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7404f1d49ef0a025828ba42224e33ca3657874e341d0cdde3bb1fed2d6facb0b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae2a6c1fad65370da9eade91936da117eb2ff339138d90a034c81a393a67e9ee
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": 0.001622375807131964,
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": 0.951,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 5301249175977984.0,
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": 0.002433563710697946,
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": 0.951,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.0016548233232746034,
411
+ "grad_norm": 0.5639609694480896,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 1.1328,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.0016872708394172426,
418
+ "grad_norm": 0.9295167922973633,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 1.0703,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.001719718355559882,
425
+ "grad_norm": 0.681804358959198,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 0.8775,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.0017521658717025211,
432
+ "grad_norm": 0.9615750312805176,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.134,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.0017521658717025211,
439
+ "eval_loss": 1.100877046585083,
440
+ "eval_runtime": 410.0074,
441
+ "eval_samples_per_second": 63.299,
442
+ "eval_steps_per_second": 7.914,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.0017846133878451605,
447
+ "grad_norm": 0.656295657157898,
448
+ "learning_rate": 5e-05,
449
+ "loss": 0.975,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.0018170609039877997,
454
+ "grad_norm": 0.7529284954071045,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.1466,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.001849508420130439,
461
+ "grad_norm": 0.729901909828186,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.9293,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.0018819559362730782,
468
+ "grad_norm": 0.6308677196502686,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 1.0554,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.0019144034524157176,
475
+ "grad_norm": 0.7009322643280029,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 1.2438,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.0019468509685583568,
482
+ "grad_norm": 0.5819316506385803,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.078,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.0019792984847009963,
489
+ "grad_norm": 0.7872710824012756,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 1.1027,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.0020117460008436355,
496
+ "grad_norm": 0.7103775143623352,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.137,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.0020441935169862747,
503
+ "grad_norm": 0.6074665188789368,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 1.1263,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.0020441935169862747,
510
+ "eval_loss": 1.096551775932312,
511
+ "eval_runtime": 410.1243,
512
+ "eval_samples_per_second": 63.281,
513
+ "eval_steps_per_second": 7.912,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.002076641033128914,
518
+ "grad_norm": 0.7665818333625793,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 0.953,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.0021090885492715534,
525
+ "grad_norm": 0.7354022860527039,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 1.1649,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.0021415360654141926,
532
+ "grad_norm": 0.8466889262199402,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 1.1085,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.0021739835815568318,
539
+ "grad_norm": 0.6907970905303955,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.1462,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.002206431097699471,
546
+ "grad_norm": 0.7935671210289001,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.8663,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.0022388786138421105,
553
+ "grad_norm": 0.6784248948097229,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.1117,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.0022713261299847497,
560
+ "grad_norm": 0.6219685673713684,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.1149,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.002303773646127389,
567
+ "grad_norm": 0.7263062000274658,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 0.7273,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.002336221162270028,
574
+ "grad_norm": 0.6051014065742493,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 1.1056,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.002336221162270028,
581
+ "eval_loss": 1.0936394929885864,
582
+ "eval_runtime": 409.7581,
583
+ "eval_samples_per_second": 63.337,
584
+ "eval_steps_per_second": 7.919,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.0023686686784126676,
589
+ "grad_norm": 0.5516490340232849,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 1.0039,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.0024011161945553068,
596
+ "grad_norm": 0.9471641182899475,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.1249,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.002433563710697946,
603
+ "grad_norm": 0.6294670104980469,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.9388,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 7977607983267840.0,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null