joelniklaus commited on
Commit
6c1cc51
1 Parent(s): 0253f1e

Training in progress, step 100000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c57da68878e140aac92e0e305cc4e36eeab07dd23d4e3e2c57aa5b74cfb989be
3
- size 2693741721
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90896b5081c841f5c896cd27201edec3a834ddf5ff97721a4988999ef95d051f
3
+ size 2693742553
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a420ea97fdbabd057832103ac7f72925c7000bc312917af36dfdf77cc15a394
3
  size 1346893675
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72210ddc5a03c29df4e488fe110d112c8b5dcd865f434eebeec4c5357bf30f3e
3
  size 1346893675
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cba4c4280fe2708987ba830760c10347d94e259759f59f6c8b17c2643d54d1d
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524c23c847bcf10bc48c85a9acbf3b41aee0f0c95369d379f5dffc1ef101a72e
3
  size 13611
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cba4c4280fe2708987ba830760c10347d94e259759f59f6c8b17c2643d54d1d
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524c23c847bcf10bc48c85a9acbf3b41aee0f0c95369d379f5dffc1ef101a72e
3
  size 13611
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cba4c4280fe2708987ba830760c10347d94e259759f59f6c8b17c2643d54d1d
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524c23c847bcf10bc48c85a9acbf3b41aee0f0c95369d379f5dffc1ef101a72e
3
  size 13611
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cba4c4280fe2708987ba830760c10347d94e259759f59f6c8b17c2643d54d1d
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524c23c847bcf10bc48c85a9acbf3b41aee0f0c95369d379f5dffc1ef101a72e
3
  size 13611
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cba4c4280fe2708987ba830760c10347d94e259759f59f6c8b17c2643d54d1d
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524c23c847bcf10bc48c85a9acbf3b41aee0f0c95369d379f5dffc1ef101a72e
3
  size 13611
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cba4c4280fe2708987ba830760c10347d94e259759f59f6c8b17c2643d54d1d
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524c23c847bcf10bc48c85a9acbf3b41aee0f0c95369d379f5dffc1ef101a72e
3
  size 13611
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cba4c4280fe2708987ba830760c10347d94e259759f59f6c8b17c2643d54d1d
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524c23c847bcf10bc48c85a9acbf3b41aee0f0c95369d379f5dffc1ef101a72e
3
  size 13611
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cba4c4280fe2708987ba830760c10347d94e259759f59f6c8b17c2643d54d1d
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524c23c847bcf10bc48c85a9acbf3b41aee0f0c95369d379f5dffc1ef101a72e
3
  size 13611
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d3c7b27bde8b1f5a5595802aeb17178a4cf1850adf7366fbf6ace3edc933ed8
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647800033a1fe4aa55a6bc8c002ddb2326a52950bde89b878eccf8a697eacefa
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.05,
5
- "global_step": 50000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -314,11 +314,319 @@
314
  "eval_samples_per_second": 165.95,
315
  "eval_steps_per_second": 2.622,
316
  "step": 50000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
317
  }
318
  ],
319
  "max_steps": 1000000,
320
  "num_train_epochs": 9223372036854775807,
321
- "total_flos": 2.9824949157888e+18,
322
  "trial_name": null,
323
  "trial_params": null
324
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.025175,
5
+ "global_step": 100000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
314
  "eval_samples_per_second": 165.95,
315
  "eval_steps_per_second": 2.622,
316
  "step": 50000
317
+ },
318
+ {
319
+ "epoch": 0.05,
320
+ "learning_rate": 9.999972660400536e-05,
321
+ "loss": 0.6375,
322
+ "step": 51000
323
+ },
324
+ {
325
+ "epoch": 0.05,
326
+ "learning_rate": 9.999890641901125e-05,
327
+ "loss": 0.7625,
328
+ "step": 52000
329
+ },
330
+ {
331
+ "epoch": 0.05,
332
+ "learning_rate": 9.999753945398704e-05,
333
+ "loss": 0.7111,
334
+ "step": 53000
335
+ },
336
+ {
337
+ "epoch": 0.05,
338
+ "learning_rate": 9.99956257238817e-05,
339
+ "loss": 0.5652,
340
+ "step": 54000
341
+ },
342
+ {
343
+ "epoch": 0.06,
344
+ "learning_rate": 9.999316524962345e-05,
345
+ "loss": 0.5796,
346
+ "step": 55000
347
+ },
348
+ {
349
+ "epoch": 0.06,
350
+ "learning_rate": 9.999015805811965e-05,
351
+ "loss": 0.7634,
352
+ "step": 56000
353
+ },
354
+ {
355
+ "epoch": 0.06,
356
+ "learning_rate": 9.998660418225645e-05,
357
+ "loss": 0.7296,
358
+ "step": 57000
359
+ },
360
+ {
361
+ "epoch": 0.06,
362
+ "learning_rate": 9.998250366089848e-05,
363
+ "loss": 0.5758,
364
+ "step": 58000
365
+ },
366
+ {
367
+ "epoch": 0.06,
368
+ "learning_rate": 9.997785653888835e-05,
369
+ "loss": 0.6196,
370
+ "step": 59000
371
+ },
372
+ {
373
+ "epoch": 0.06,
374
+ "learning_rate": 9.997266286704631e-05,
375
+ "loss": 0.7018,
376
+ "step": 60000
377
+ },
378
+ {
379
+ "epoch": 0.06,
380
+ "learning_rate": 9.996692270216947e-05,
381
+ "loss": 0.6875,
382
+ "step": 61000
383
+ },
384
+ {
385
+ "epoch": 0.06,
386
+ "learning_rate": 9.996063610703137e-05,
387
+ "loss": 0.6113,
388
+ "step": 62000
389
+ },
390
+ {
391
+ "epoch": 0.06,
392
+ "learning_rate": 9.995380315038119e-05,
393
+ "loss": 0.7141,
394
+ "step": 63000
395
+ },
396
+ {
397
+ "epoch": 0.06,
398
+ "learning_rate": 9.994642390694308e-05,
399
+ "loss": 0.814,
400
+ "step": 64000
401
+ },
402
+ {
403
+ "epoch": 0.07,
404
+ "learning_rate": 9.993849845741524e-05,
405
+ "loss": 0.7573,
406
+ "step": 65000
407
+ },
408
+ {
409
+ "epoch": 0.07,
410
+ "learning_rate": 9.993002688846913e-05,
411
+ "loss": 0.6522,
412
+ "step": 66000
413
+ },
414
+ {
415
+ "epoch": 0.07,
416
+ "learning_rate": 9.992100929274846e-05,
417
+ "loss": 0.6774,
418
+ "step": 67000
419
+ },
420
+ {
421
+ "epoch": 0.07,
422
+ "learning_rate": 9.991144576886823e-05,
423
+ "loss": 0.7855,
424
+ "step": 68000
425
+ },
426
+ {
427
+ "epoch": 0.07,
428
+ "learning_rate": 9.990133642141359e-05,
429
+ "loss": 0.7461,
430
+ "step": 69000
431
+ },
432
+ {
433
+ "epoch": 0.07,
434
+ "learning_rate": 9.989068136093873e-05,
435
+ "loss": 0.634,
436
+ "step": 70000
437
+ },
438
+ {
439
+ "epoch": 0.07,
440
+ "learning_rate": 9.987948070396571e-05,
441
+ "loss": 0.6621,
442
+ "step": 71000
443
+ },
444
+ {
445
+ "epoch": 0.07,
446
+ "learning_rate": 9.986773457298311e-05,
447
+ "loss": 0.769,
448
+ "step": 72000
449
+ },
450
+ {
451
+ "epoch": 0.07,
452
+ "learning_rate": 9.985544309644475e-05,
453
+ "loss": 0.7128,
454
+ "step": 73000
455
+ },
456
+ {
457
+ "epoch": 0.07,
458
+ "learning_rate": 9.984260640876821e-05,
459
+ "loss": 0.6125,
460
+ "step": 74000
461
+ },
462
+ {
463
+ "epoch": 1.0,
464
+ "learning_rate": 9.98292246503335e-05,
465
+ "loss": 0.6764,
466
+ "step": 75000
467
+ },
468
+ {
469
+ "epoch": 1.0,
470
+ "learning_rate": 9.981529796748134e-05,
471
+ "loss": 0.7392,
472
+ "step": 76000
473
+ },
474
+ {
475
+ "epoch": 1.0,
476
+ "learning_rate": 9.980082651251175e-05,
477
+ "loss": 0.6323,
478
+ "step": 77000
479
+ },
480
+ {
481
+ "epoch": 1.0,
482
+ "learning_rate": 9.97858104436822e-05,
483
+ "loss": 0.6628,
484
+ "step": 78000
485
+ },
486
+ {
487
+ "epoch": 1.0,
488
+ "learning_rate": 9.977024992520602e-05,
489
+ "loss": 0.7715,
490
+ "step": 79000
491
+ },
492
+ {
493
+ "epoch": 1.01,
494
+ "learning_rate": 9.975414512725057e-05,
495
+ "loss": 0.7154,
496
+ "step": 80000
497
+ },
498
+ {
499
+ "epoch": 1.01,
500
+ "learning_rate": 9.973749622593534e-05,
501
+ "loss": 0.6102,
502
+ "step": 81000
503
+ },
504
+ {
505
+ "epoch": 1.01,
506
+ "learning_rate": 9.972030340333001e-05,
507
+ "loss": 0.6467,
508
+ "step": 82000
509
+ },
510
+ {
511
+ "epoch": 1.01,
512
+ "learning_rate": 9.970256684745258e-05,
513
+ "loss": 0.7534,
514
+ "step": 83000
515
+ },
516
+ {
517
+ "epoch": 1.01,
518
+ "learning_rate": 9.968428675226714e-05,
519
+ "loss": 0.704,
520
+ "step": 84000
521
+ },
522
+ {
523
+ "epoch": 1.01,
524
+ "learning_rate": 9.966546331768191e-05,
525
+ "loss": 0.6225,
526
+ "step": 85000
527
+ },
528
+ {
529
+ "epoch": 1.01,
530
+ "learning_rate": 9.964609674954696e-05,
531
+ "loss": 0.6437,
532
+ "step": 86000
533
+ },
534
+ {
535
+ "epoch": 1.01,
536
+ "learning_rate": 9.962618725965196e-05,
537
+ "loss": 0.754,
538
+ "step": 87000
539
+ },
540
+ {
541
+ "epoch": 1.01,
542
+ "learning_rate": 9.96057350657239e-05,
543
+ "loss": 0.6902,
544
+ "step": 88000
545
+ },
546
+ {
547
+ "epoch": 1.01,
548
+ "learning_rate": 9.95847403914247e-05,
549
+ "loss": 0.6096,
550
+ "step": 89000
551
+ },
552
+ {
553
+ "epoch": 1.02,
554
+ "learning_rate": 9.956320346634876e-05,
555
+ "loss": 0.6426,
556
+ "step": 90000
557
+ },
558
+ {
559
+ "epoch": 1.02,
560
+ "learning_rate": 9.954112452602045e-05,
561
+ "loss": 0.7444,
562
+ "step": 91000
563
+ },
564
+ {
565
+ "epoch": 1.02,
566
+ "learning_rate": 9.95185038118915e-05,
567
+ "loss": 0.6821,
568
+ "step": 92000
569
+ },
570
+ {
571
+ "epoch": 1.02,
572
+ "learning_rate": 9.949534157133844e-05,
573
+ "loss": 0.5948,
574
+ "step": 93000
575
+ },
576
+ {
577
+ "epoch": 1.02,
578
+ "learning_rate": 9.94716380576598e-05,
579
+ "loss": 0.6266,
580
+ "step": 94000
581
+ },
582
+ {
583
+ "epoch": 1.02,
584
+ "learning_rate": 9.944739353007344e-05,
585
+ "loss": 0.7387,
586
+ "step": 95000
587
+ },
588
+ {
589
+ "epoch": 1.02,
590
+ "learning_rate": 9.942260825371358e-05,
591
+ "loss": 0.6734,
592
+ "step": 96000
593
+ },
594
+ {
595
+ "epoch": 1.02,
596
+ "learning_rate": 9.939728249962807e-05,
597
+ "loss": 0.5943,
598
+ "step": 97000
599
+ },
600
+ {
601
+ "epoch": 1.02,
602
+ "learning_rate": 9.937141654477528e-05,
603
+ "loss": 0.6332,
604
+ "step": 98000
605
+ },
606
+ {
607
+ "epoch": 1.02,
608
+ "learning_rate": 9.934501067202117e-05,
609
+ "loss": 0.7306,
610
+ "step": 99000
611
+ },
612
+ {
613
+ "epoch": 1.03,
614
+ "learning_rate": 9.931806517013612e-05,
615
+ "loss": 0.6654,
616
+ "step": 100000
617
+ },
618
+ {
619
+ "epoch": 1.03,
620
+ "eval_loss": 0.4750686585903168,
621
+ "eval_runtime": 31.6698,
622
+ "eval_samples_per_second": 157.879,
623
+ "eval_steps_per_second": 2.494,
624
+ "step": 100000
625
  }
626
  ],
627
  "max_steps": 1000000,
628
  "num_train_epochs": 9223372036854775807,
629
+ "total_flos": 5.965012200289468e+18,
630
  "trial_name": null,
631
  "trial_params": null
632
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:845508cc38007d8b2a7a8855373b6b11d5c4e94a423856e2b9c4963c713988dc
3
- size 3439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2fdc390cc059f4ea67f02d60dce87ec4a8bb54eedf9e688c28d4d67ce830c58
3
+ size 3503
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a420ea97fdbabd057832103ac7f72925c7000bc312917af36dfdf77cc15a394
3
  size 1346893675
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72210ddc5a03c29df4e488fe110d112c8b5dcd865f434eebeec4c5357bf30f3e
3
  size 1346893675
runs/Feb17_16-44-14_t1v-n-91d26b69-w-0/1676652795.6460006/events.out.tfevents.1676652795.t1v-n-91d26b69-w-0.1590282.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db9345dd823268b8790c224dc1959d0e880174954598e53768e07e012d8eb154
3
+ size 5514
runs/Feb17_16-44-14_t1v-n-91d26b69-w-0/events.out.tfevents.1676652795.t1v-n-91d26b69-w-0.1590282.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53d4d95acff7c0420d87d6e952d529ddf6986facb47c97e4b3fca90e141c906
3
+ size 12130
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:845508cc38007d8b2a7a8855373b6b11d5c4e94a423856e2b9c4963c713988dc
3
- size 3439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2fdc390cc059f4ea67f02d60dce87ec4a8bb54eedf9e688c28d4d67ce830c58
3
+ size 3503