lesso08 commited on
Commit
9e19805
·
verified ·
1 Parent(s): eb41ec4

Training in progress, step 75, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b945c72b238d8c8bfe92aaaddc11ee42bba244ef212e5053c0d8353dfdfae28
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c34bccab4467f35f4829ca04f03fdb15facf84448a43d61de1dd553e4ca7037
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ef6f827bb94fd9f00d5c01064707e25080a397ccf4522b1a36253453f648840
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6b27cd95f006ac9ce544d36cedf86676a982730c0174955991ca4cc0cd6105
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3182bde371d68a198b64a8220fa0b6fe0537449e5a6543e1127aeb44513ea58
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1902eeb51fe92d3e250c39d6fbb85959781ab19bfc1376401ea409486445eba3
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": 0.24330900243309003,
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": 1.1838,
407
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408
  }
409
  ],
410
  "logging_steps": 1,
@@ -424,7 +623,7 @@
424
  "attributes": {}
425
  }
426
  },
427
- "total_flos": 3.820719510336307e+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": 0.36496350364963503,
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": 1.1838,
407
  "step": 50
408
+ },
409
+ {
410
+ "epoch": 0.24817518248175183,
411
+ "grad_norm": 1.2569478750228882,
412
+ "learning_rate": 5.695865504800327e-05,
413
+ "loss": 1.3188,
414
+ "step": 51
415
+ },
416
+ {
417
+ "epoch": 0.25304136253041365,
418
+ "grad_norm": 0.9744678735733032,
419
+ "learning_rate": 5.522642316338268e-05,
420
+ "loss": 1.0088,
421
+ "step": 52
422
+ },
423
+ {
424
+ "epoch": 0.25790754257907544,
425
+ "grad_norm": 1.0326542854309082,
426
+ "learning_rate": 5.348782368720626e-05,
427
+ "loss": 1.3964,
428
+ "step": 53
429
+ },
430
+ {
431
+ "epoch": 0.26277372262773724,
432
+ "grad_norm": 1.4304847717285156,
433
+ "learning_rate": 5.174497483512506e-05,
434
+ "loss": 1.2375,
435
+ "step": 54
436
+ },
437
+ {
438
+ "epoch": 0.26277372262773724,
439
+ "eval_loss": 1.0286833047866821,
440
+ "eval_runtime": 19.0435,
441
+ "eval_samples_per_second": 9.084,
442
+ "eval_steps_per_second": 1.155,
443
+ "step": 54
444
+ },
445
+ {
446
+ "epoch": 0.26763990267639903,
447
+ "grad_norm": 1.2375237941741943,
448
+ "learning_rate": 5e-05,
449
+ "loss": 1.2123,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.2725060827250608,
454
+ "grad_norm": 1.014127254486084,
455
+ "learning_rate": 4.825502516487497e-05,
456
+ "loss": 1.3642,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.2773722627737226,
461
+ "grad_norm": 1.0220732688903809,
462
+ "learning_rate": 4.6512176312793736e-05,
463
+ "loss": 0.8832,
464
+ "step": 57
465
+ },
466
+ {
467
+ "epoch": 0.2822384428223844,
468
+ "grad_norm": 1.0092318058013916,
469
+ "learning_rate": 4.477357683661734e-05,
470
+ "loss": 0.7852,
471
+ "step": 58
472
+ },
473
+ {
474
+ "epoch": 0.2871046228710462,
475
+ "grad_norm": 0.9593155980110168,
476
+ "learning_rate": 4.3041344951996746e-05,
477
+ "loss": 0.9424,
478
+ "step": 59
479
+ },
480
+ {
481
+ "epoch": 0.291970802919708,
482
+ "grad_norm": 1.1366311311721802,
483
+ "learning_rate": 4.131759111665349e-05,
484
+ "loss": 1.3309,
485
+ "step": 60
486
+ },
487
+ {
488
+ "epoch": 0.29683698296836986,
489
+ "grad_norm": 1.061318039894104,
490
+ "learning_rate": 3.960441545911204e-05,
491
+ "loss": 0.8699,
492
+ "step": 61
493
+ },
494
+ {
495
+ "epoch": 0.30170316301703165,
496
+ "grad_norm": 1.5996885299682617,
497
+ "learning_rate": 3.790390522001662e-05,
498
+ "loss": 1.4451,
499
+ "step": 62
500
+ },
501
+ {
502
+ "epoch": 0.30656934306569344,
503
+ "grad_norm": 1.3761976957321167,
504
+ "learning_rate": 3.6218132209150045e-05,
505
+ "loss": 1.2438,
506
+ "step": 63
507
+ },
508
+ {
509
+ "epoch": 0.30656934306569344,
510
+ "eval_loss": 1.0191401243209839,
511
+ "eval_runtime": 19.0485,
512
+ "eval_samples_per_second": 9.082,
513
+ "eval_steps_per_second": 1.155,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.31143552311435524,
518
+ "grad_norm": 1.4792134761810303,
519
+ "learning_rate": 3.4549150281252636e-05,
520
+ "loss": 1.4994,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.31630170316301703,
525
+ "grad_norm": 1.02501380443573,
526
+ "learning_rate": 3.289899283371657e-05,
527
+ "loss": 0.8248,
528
+ "step": 65
529
+ },
530
+ {
531
+ "epoch": 0.32116788321167883,
532
+ "grad_norm": 1.9706014394760132,
533
+ "learning_rate": 3.12696703292044e-05,
534
+ "loss": 1.2776,
535
+ "step": 66
536
+ },
537
+ {
538
+ "epoch": 0.3260340632603406,
539
+ "grad_norm": 1.3999546766281128,
540
+ "learning_rate": 2.9663167846209998e-05,
541
+ "loss": 1.1599,
542
+ "step": 67
543
+ },
544
+ {
545
+ "epoch": 0.3309002433090024,
546
+ "grad_norm": 1.561223030090332,
547
+ "learning_rate": 2.8081442660546125e-05,
548
+ "loss": 0.8594,
549
+ "step": 68
550
+ },
551
+ {
552
+ "epoch": 0.3357664233576642,
553
+ "grad_norm": 1.1113779544830322,
554
+ "learning_rate": 2.6526421860705473e-05,
555
+ "loss": 1.0403,
556
+ "step": 69
557
+ },
558
+ {
559
+ "epoch": 0.340632603406326,
560
+ "grad_norm": 1.1394065618515015,
561
+ "learning_rate": 2.500000000000001e-05,
562
+ "loss": 1.4539,
563
+ "step": 70
564
+ },
565
+ {
566
+ "epoch": 0.34549878345498786,
567
+ "grad_norm": 1.26051926612854,
568
+ "learning_rate": 2.350403678833976e-05,
569
+ "loss": 1.5036,
570
+ "step": 71
571
+ },
572
+ {
573
+ "epoch": 0.35036496350364965,
574
+ "grad_norm": 0.9440858960151672,
575
+ "learning_rate": 2.2040354826462668e-05,
576
+ "loss": 1.1182,
577
+ "step": 72
578
+ },
579
+ {
580
+ "epoch": 0.35036496350364965,
581
+ "eval_loss": 1.0112653970718384,
582
+ "eval_runtime": 19.0703,
583
+ "eval_samples_per_second": 9.072,
584
+ "eval_steps_per_second": 1.154,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.35523114355231145,
589
+ "grad_norm": 1.110795021057129,
590
+ "learning_rate": 2.061073738537635e-05,
591
+ "loss": 0.8803,
592
+ "step": 73
593
+ },
594
+ {
595
+ "epoch": 0.36009732360097324,
596
+ "grad_norm": 1.3027766942977905,
597
+ "learning_rate": 1.9216926233717085e-05,
598
+ "loss": 1.238,
599
+ "step": 74
600
+ },
601
+ {
602
+ "epoch": 0.36496350364963503,
603
+ "grad_norm": 1.2464637756347656,
604
+ "learning_rate": 1.7860619515673033e-05,
605
+ "loss": 0.8754,
606
+ "step": 75
607
  }
608
  ],
609
  "logging_steps": 1,
 
623
  "attributes": {}
624
  }
625
  },
626
+ "total_flos": 5.675437719237427e+16,
627
  "train_batch_size": 8,
628
  "trial_name": null,
629
  "trial_params": null