irishprancer commited on
Commit
cdc36ea
·
verified ·
1 Parent(s): 72976cc

Training in progress, step 750, 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:b208fb04bd797b877fa1dfdacd8a72771192807ce16faf614c1db8f415c46813
3
  size 527048968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652d63c68dfe1e35e6942371c8f9f4a9f19ab99ae5f4ddbcdfca63ce319f3780
3
  size 527048968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bda7e786e2e656f96080f96850aaef8ced5c1e58267af79f77f9d2d7ca8a316
3
  size 1054136250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd325e085efecfd52fda63e3ae981a902519e53e5102f41867a1ca760f848916
3
  size 1054136250
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed14e15604e1097b80da74a65c68f380dc6bb673bf5694a945c25e7931ad5a75
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d591cd4a87db6ff7862986fcbd71a7ea08ac34a6c4ca00eb88fbc6e4ccf1c5bd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb248e7cc2fe7b509c9e866be7b72af3b33225d8b86373c1a62393cc3a24f4da
3
  size 1256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47df519d3e34f85833ffe9513be298918979811657719c019fec7ab68351e14
3
  size 1256
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.7268816828727722,
3
- "best_model_checkpoint": "./output/checkpoint-450",
4
- "epoch": 10.0,
5
  "eval_steps": 150,
6
- "global_step": 450,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -346,6 +346,232 @@
346
  "eval_samples_per_second": 23.528,
347
  "eval_steps_per_second": 23.528,
348
  "step": 450
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
349
  }
350
  ],
351
  "logging_steps": 10,
@@ -365,7 +591,7 @@
365
  "attributes": {}
366
  }
367
  },
368
- "total_flos": 4801636770840576.0,
369
  "train_batch_size": 2,
370
  "trial_name": null,
371
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.7210294008255005,
3
+ "best_model_checkpoint": "./output/checkpoint-750",
4
+ "epoch": 16.666666666666668,
5
  "eval_steps": 150,
6
+ "global_step": 750,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
346
  "eval_samples_per_second": 23.528,
347
  "eval_steps_per_second": 23.528,
348
  "step": 450
349
+ },
350
+ {
351
+ "epoch": 10.222222222222221,
352
+ "grad_norm": 2.2311553955078125,
353
+ "learning_rate": 2.9996147467351836e-05,
354
+ "loss": 0.5062,
355
+ "step": 460
356
+ },
357
+ {
358
+ "epoch": 10.444444444444445,
359
+ "grad_norm": 1.4143763780593872,
360
+ "learning_rate": 2.9995930474939753e-05,
361
+ "loss": 0.4908,
362
+ "step": 470
363
+ },
364
+ {
365
+ "epoch": 10.666666666666666,
366
+ "grad_norm": 1.9285305738449097,
367
+ "learning_rate": 2.9995707538619954e-05,
368
+ "loss": 0.6355,
369
+ "step": 480
370
+ },
371
+ {
372
+ "epoch": 10.88888888888889,
373
+ "grad_norm": 2.1390364170074463,
374
+ "learning_rate": 2.9995478658480802e-05,
375
+ "loss": 0.5531,
376
+ "step": 490
377
+ },
378
+ {
379
+ "epoch": 11.11111111111111,
380
+ "grad_norm": 1.8684849739074707,
381
+ "learning_rate": 2.9995243834613023e-05,
382
+ "loss": 0.5237,
383
+ "step": 500
384
+ },
385
+ {
386
+ "epoch": 11.333333333333334,
387
+ "grad_norm": 1.6750541925430298,
388
+ "learning_rate": 2.9995003067109687e-05,
389
+ "loss": 0.5385,
390
+ "step": 510
391
+ },
392
+ {
393
+ "epoch": 11.555555555555555,
394
+ "grad_norm": 2.6402785778045654,
395
+ "learning_rate": 2.9994756356066226e-05,
396
+ "loss": 0.5847,
397
+ "step": 520
398
+ },
399
+ {
400
+ "epoch": 11.777777777777779,
401
+ "grad_norm": 2.2594568729400635,
402
+ "learning_rate": 2.999450370158044e-05,
403
+ "loss": 0.5341,
404
+ "step": 530
405
+ },
406
+ {
407
+ "epoch": 12.0,
408
+ "grad_norm": 1.5283032655715942,
409
+ "learning_rate": 2.9994245103752457e-05,
410
+ "loss": 0.5243,
411
+ "step": 540
412
+ },
413
+ {
414
+ "epoch": 12.222222222222221,
415
+ "grad_norm": 1.2468581199645996,
416
+ "learning_rate": 2.999398056268479e-05,
417
+ "loss": 0.5354,
418
+ "step": 550
419
+ },
420
+ {
421
+ "epoch": 12.444444444444445,
422
+ "grad_norm": 1.4768636226654053,
423
+ "learning_rate": 2.9993710078482286e-05,
424
+ "loss": 0.4149,
425
+ "step": 560
426
+ },
427
+ {
428
+ "epoch": 12.666666666666666,
429
+ "grad_norm": 3.385610580444336,
430
+ "learning_rate": 2.9993433651252164e-05,
431
+ "loss": 0.6199,
432
+ "step": 570
433
+ },
434
+ {
435
+ "epoch": 12.88888888888889,
436
+ "grad_norm": 1.4733967781066895,
437
+ "learning_rate": 2.9993151281103986e-05,
438
+ "loss": 0.5354,
439
+ "step": 580
440
+ },
441
+ {
442
+ "epoch": 13.11111111111111,
443
+ "grad_norm": 2.435899019241333,
444
+ "learning_rate": 2.9992862968149675e-05,
445
+ "loss": 0.4177,
446
+ "step": 590
447
+ },
448
+ {
449
+ "epoch": 13.333333333333334,
450
+ "grad_norm": 2.4628303050994873,
451
+ "learning_rate": 2.9992568712503513e-05,
452
+ "loss": 0.5327,
453
+ "step": 600
454
+ },
455
+ {
456
+ "epoch": 13.333333333333334,
457
+ "eval_loss": 0.7213956117630005,
458
+ "eval_runtime": 0.4476,
459
+ "eval_samples_per_second": 22.343,
460
+ "eval_steps_per_second": 22.343,
461
+ "step": 600
462
+ },
463
+ {
464
+ "epoch": 13.555555555555555,
465
+ "grad_norm": 2.3349859714508057,
466
+ "learning_rate": 2.9992268514282122e-05,
467
+ "loss": 0.5655,
468
+ "step": 610
469
+ },
470
+ {
471
+ "epoch": 13.777777777777779,
472
+ "grad_norm": 2.215526580810547,
473
+ "learning_rate": 2.99919623736045e-05,
474
+ "loss": 0.4406,
475
+ "step": 620
476
+ },
477
+ {
478
+ "epoch": 14.0,
479
+ "grad_norm": 2.2699978351593018,
480
+ "learning_rate": 2.9991650290591996e-05,
481
+ "loss": 0.6034,
482
+ "step": 630
483
+ },
484
+ {
485
+ "epoch": 14.222222222222221,
486
+ "grad_norm": 2.2520437240600586,
487
+ "learning_rate": 2.99913322653683e-05,
488
+ "loss": 0.492,
489
+ "step": 640
490
+ },
491
+ {
492
+ "epoch": 14.444444444444445,
493
+ "grad_norm": 1.8439189195632935,
494
+ "learning_rate": 2.9991008298059473e-05,
495
+ "loss": 0.5013,
496
+ "step": 650
497
+ },
498
+ {
499
+ "epoch": 14.666666666666666,
500
+ "grad_norm": 1.5318201780319214,
501
+ "learning_rate": 2.9990678388793924e-05,
502
+ "loss": 0.5316,
503
+ "step": 660
504
+ },
505
+ {
506
+ "epoch": 14.88888888888889,
507
+ "grad_norm": 1.2852894067764282,
508
+ "learning_rate": 2.999034253770242e-05,
509
+ "loss": 0.4578,
510
+ "step": 670
511
+ },
512
+ {
513
+ "epoch": 15.11111111111111,
514
+ "grad_norm": 2.532104015350342,
515
+ "learning_rate": 2.9990000744918076e-05,
516
+ "loss": 0.4492,
517
+ "step": 680
518
+ },
519
+ {
520
+ "epoch": 15.333333333333334,
521
+ "grad_norm": 1.6051527261734009,
522
+ "learning_rate": 2.9989653010576372e-05,
523
+ "loss": 0.4531,
524
+ "step": 690
525
+ },
526
+ {
527
+ "epoch": 15.555555555555555,
528
+ "grad_norm": 1.4627478122711182,
529
+ "learning_rate": 2.9989299334815138e-05,
530
+ "loss": 0.4804,
531
+ "step": 700
532
+ },
533
+ {
534
+ "epoch": 15.777777777777779,
535
+ "grad_norm": 2.238284111022949,
536
+ "learning_rate": 2.9988939717774558e-05,
537
+ "loss": 0.524,
538
+ "step": 710
539
+ },
540
+ {
541
+ "epoch": 16.0,
542
+ "grad_norm": 1.3457872867584229,
543
+ "learning_rate": 2.9988574159597174e-05,
544
+ "loss": 0.5107,
545
+ "step": 720
546
+ },
547
+ {
548
+ "epoch": 16.22222222222222,
549
+ "grad_norm": 2.1465327739715576,
550
+ "learning_rate": 2.9988202660427887e-05,
551
+ "loss": 0.4642,
552
+ "step": 730
553
+ },
554
+ {
555
+ "epoch": 16.444444444444443,
556
+ "grad_norm": 3.066289186477661,
557
+ "learning_rate": 2.9987825220413937e-05,
558
+ "loss": 0.5349,
559
+ "step": 740
560
+ },
561
+ {
562
+ "epoch": 16.666666666666668,
563
+ "grad_norm": 1.9061943292617798,
564
+ "learning_rate": 2.998744183970494e-05,
565
+ "loss": 0.4266,
566
+ "step": 750
567
+ },
568
+ {
569
+ "epoch": 16.666666666666668,
570
+ "eval_loss": 0.7210294008255005,
571
+ "eval_runtime": 0.405,
572
+ "eval_samples_per_second": 24.693,
573
+ "eval_steps_per_second": 24.693,
574
+ "step": 750
575
  }
576
  ],
577
  "logging_steps": 10,
 
591
  "attributes": {}
592
  }
593
  },
594
+ "total_flos": 7981049240027136.0,
595
  "train_batch_size": 2,
596
  "trial_name": null,
597
  "trial_params": null