joelniklaus commited on
Commit
4024b00
1 Parent(s): 5048b80

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:d4517ef0a6623d4ab1381ef412e672097c3277a9ebf641390af82a00343bd1b5
3
- size 885324633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3c0ae558d5c6797849beda9e8344cad53ae9b53b00529c334849fb4d05ff27d
3
+ size 885325017
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f22933984e7fa2ac0e3974e919f9b0f04b81f66db9c9cf35e614e54253d9183c
3
  size 442675755
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf3179e77f86e938834ad7a2cb0522bcd0f4403c0978f2db3b2fa245ace152d8
3
  size 442675755
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a465909d3e4414492bf99cb1c0ef6e5b603dd2662f92c7cf1f46ba416f676cd
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bdf286d14621599873d5f47bdb57cd91e37223a643c13ee02de7f7aaacd2e
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 sha256:8a465909d3e4414492bf99cb1c0ef6e5b603dd2662f92c7cf1f46ba416f676cd
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bdf286d14621599873d5f47bdb57cd91e37223a643c13ee02de7f7aaacd2e
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 sha256:8a465909d3e4414492bf99cb1c0ef6e5b603dd2662f92c7cf1f46ba416f676cd
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bdf286d14621599873d5f47bdb57cd91e37223a643c13ee02de7f7aaacd2e
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 sha256:8a465909d3e4414492bf99cb1c0ef6e5b603dd2662f92c7cf1f46ba416f676cd
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bdf286d14621599873d5f47bdb57cd91e37223a643c13ee02de7f7aaacd2e
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 sha256:8a465909d3e4414492bf99cb1c0ef6e5b603dd2662f92c7cf1f46ba416f676cd
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bdf286d14621599873d5f47bdb57cd91e37223a643c13ee02de7f7aaacd2e
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 sha256:8a465909d3e4414492bf99cb1c0ef6e5b603dd2662f92c7cf1f46ba416f676cd
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bdf286d14621599873d5f47bdb57cd91e37223a643c13ee02de7f7aaacd2e
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 sha256:8a465909d3e4414492bf99cb1c0ef6e5b603dd2662f92c7cf1f46ba416f676cd
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bdf286d14621599873d5f47bdb57cd91e37223a643c13ee02de7f7aaacd2e
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 sha256:8a465909d3e4414492bf99cb1c0ef6e5b603dd2662f92c7cf1f46ba416f676cd
3
  size 13611
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bdf286d14621599873d5f47bdb57cd91e37223a643c13ee02de7f7aaacd2e
3
  size 13611
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4eda5fed79fbfae57d1a589b135999ab70f7c329a9938c428058fd62dc77c658
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4178362c6bd24374be7907f1b74df811389bf304534a9b4cb11df3bada4d661b
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": 32.00056,
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": 300.462,
315
  "eval_steps_per_second": 2.404,
316
  "step": 50000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
317
  }
318
  ],
319
  "max_steps": 200000,
320
  "num_train_epochs": 9223372036854775807,
321
- "total_flos": 8.424046934800466e+17,
322
  "trial_name": null,
323
  "trial_params": null
324
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 64.00112,
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": 300.462,
315
  "eval_steps_per_second": 2.404,
316
  "step": 50000
317
+ },
318
+ {
319
+ "epoch": 32.01,
320
+ "learning_rate": 8.894386393810563e-05,
321
+ "loss": 0.7953,
322
+ "step": 51000
323
+ },
324
+ {
325
+ "epoch": 33.0,
326
+ "learning_rate": 8.842005554284296e-05,
327
+ "loss": 0.7928,
328
+ "step": 52000
329
+ },
330
+ {
331
+ "epoch": 33.01,
332
+ "learning_rate": 8.788574348801675e-05,
333
+ "loss": 0.8643,
334
+ "step": 53000
335
+ },
336
+ {
337
+ "epoch": 34.0,
338
+ "learning_rate": 8.73410738492077e-05,
339
+ "loss": 0.7746,
340
+ "step": 54000
341
+ },
342
+ {
343
+ "epoch": 35.0,
344
+ "learning_rate": 8.678619553365659e-05,
345
+ "loss": 0.8094,
346
+ "step": 55000
347
+ },
348
+ {
349
+ "epoch": 35.01,
350
+ "learning_rate": 8.622126023955446e-05,
351
+ "loss": 0.8318,
352
+ "step": 56000
353
+ },
354
+ {
355
+ "epoch": 36.0,
356
+ "learning_rate": 8.564642241456986e-05,
357
+ "loss": 0.7601,
358
+ "step": 57000
359
+ },
360
+ {
361
+ "epoch": 37.0,
362
+ "learning_rate": 8.506183921362443e-05,
363
+ "loss": 0.8153,
364
+ "step": 58000
365
+ },
366
+ {
367
+ "epoch": 37.01,
368
+ "learning_rate": 8.44676704559283e-05,
369
+ "loss": 0.8049,
370
+ "step": 59000
371
+ },
372
+ {
373
+ "epoch": 38.0,
374
+ "learning_rate": 8.386407858128706e-05,
375
+ "loss": 0.758,
376
+ "step": 60000
377
+ },
378
+ {
379
+ "epoch": 39.0,
380
+ "learning_rate": 8.32512286056924e-05,
381
+ "loss": 0.8346,
382
+ "step": 61000
383
+ },
384
+ {
385
+ "epoch": 39.01,
386
+ "learning_rate": 8.262928807620843e-05,
387
+ "loss": 0.7726,
388
+ "step": 62000
389
+ },
390
+ {
391
+ "epoch": 40.0,
392
+ "learning_rate": 8.199842702516583e-05,
393
+ "loss": 0.754,
394
+ "step": 63000
395
+ },
396
+ {
397
+ "epoch": 41.0,
398
+ "learning_rate": 8.135881792367686e-05,
399
+ "loss": 0.8374,
400
+ "step": 64000
401
+ },
402
+ {
403
+ "epoch": 41.01,
404
+ "learning_rate": 8.07106356344834e-05,
405
+ "loss": 0.7596,
406
+ "step": 65000
407
+ },
408
+ {
409
+ "epoch": 42.0,
410
+ "learning_rate": 8.005405736415126e-05,
411
+ "loss": 0.76,
412
+ "step": 66000
413
+ },
414
+ {
415
+ "epoch": 42.01,
416
+ "learning_rate": 7.938926261462366e-05,
417
+ "loss": 0.8258,
418
+ "step": 67000
419
+ },
420
+ {
421
+ "epoch": 43.0,
422
+ "learning_rate": 7.871643313414718e-05,
423
+ "loss": 0.7399,
424
+ "step": 68000
425
+ },
426
+ {
427
+ "epoch": 44.0,
428
+ "learning_rate": 7.803575286758364e-05,
429
+ "loss": 0.7789,
430
+ "step": 69000
431
+ },
432
+ {
433
+ "epoch": 44.01,
434
+ "learning_rate": 7.734740790612136e-05,
435
+ "loss": 0.801,
436
+ "step": 70000
437
+ },
438
+ {
439
+ "epoch": 45.0,
440
+ "learning_rate": 7.66515864363997e-05,
441
+ "loss": 0.729,
442
+ "step": 71000
443
+ },
444
+ {
445
+ "epoch": 46.0,
446
+ "learning_rate": 7.594847868906076e-05,
447
+ "loss": 0.7974,
448
+ "step": 72000
449
+ },
450
+ {
451
+ "epoch": 46.01,
452
+ "learning_rate": 7.52382768867422e-05,
453
+ "loss": 0.7615,
454
+ "step": 73000
455
+ },
456
+ {
457
+ "epoch": 47.0,
458
+ "learning_rate": 7.452117519152542e-05,
459
+ "loss": 0.7302,
460
+ "step": 74000
461
+ },
462
+ {
463
+ "epoch": 48.0,
464
+ "learning_rate": 7.379736965185368e-05,
465
+ "loss": 0.8065,
466
+ "step": 75000
467
+ },
468
+ {
469
+ "epoch": 48.01,
470
+ "learning_rate": 7.30670581489344e-05,
471
+ "loss": 0.7451,
472
+ "step": 76000
473
+ },
474
+ {
475
+ "epoch": 49.0,
476
+ "learning_rate": 7.233044034264034e-05,
477
+ "loss": 0.7263,
478
+ "step": 77000
479
+ },
480
+ {
481
+ "epoch": 50.0,
482
+ "learning_rate": 7.158771761692464e-05,
483
+ "loss": 0.8105,
484
+ "step": 78000
485
+ },
486
+ {
487
+ "epoch": 50.01,
488
+ "learning_rate": 7.083909302476453e-05,
489
+ "loss": 0.7318,
490
+ "step": 79000
491
+ },
492
+ {
493
+ "epoch": 51.0,
494
+ "learning_rate": 7.008477123264848e-05,
495
+ "loss": 0.7394,
496
+ "step": 80000
497
+ },
498
+ {
499
+ "epoch": 51.01,
500
+ "learning_rate": 6.932495846462261e-05,
501
+ "loss": 0.7932,
502
+ "step": 81000
503
+ },
504
+ {
505
+ "epoch": 52.0,
506
+ "learning_rate": 6.855986244591104e-05,
507
+ "loss": 0.7127,
508
+ "step": 82000
509
+ },
510
+ {
511
+ "epoch": 53.0,
512
+ "learning_rate": 6.778969234612584e-05,
513
+ "loss": 0.7575,
514
+ "step": 83000
515
+ },
516
+ {
517
+ "epoch": 53.01,
518
+ "learning_rate": 6.701465872208216e-05,
519
+ "loss": 0.7684,
520
+ "step": 84000
521
+ },
522
+ {
523
+ "epoch": 54.0,
524
+ "learning_rate": 6.623497346023418e-05,
525
+ "loss": 0.7064,
526
+ "step": 85000
527
+ },
528
+ {
529
+ "epoch": 55.0,
530
+ "learning_rate": 6.545084971874738e-05,
531
+ "loss": 0.7796,
532
+ "step": 86000
533
+ },
534
+ {
535
+ "epoch": 55.01,
536
+ "learning_rate": 6.466250186922325e-05,
537
+ "loss": 0.7313,
538
+ "step": 87000
539
+ },
540
+ {
541
+ "epoch": 56.0,
542
+ "learning_rate": 6.387014543809223e-05,
543
+ "loss": 0.7073,
544
+ "step": 88000
545
+ },
546
+ {
547
+ "epoch": 57.0,
548
+ "learning_rate": 6.307399704769099e-05,
549
+ "loss": 0.7876,
550
+ "step": 89000
551
+ },
552
+ {
553
+ "epoch": 57.01,
554
+ "learning_rate": 6.227427435703997e-05,
555
+ "loss": 0.718,
556
+ "step": 90000
557
+ },
558
+ {
559
+ "epoch": 58.0,
560
+ "learning_rate": 6.147119600233758e-05,
561
+ "loss": 0.7123,
562
+ "step": 91000
563
+ },
564
+ {
565
+ "epoch": 59.0,
566
+ "learning_rate": 6.066498153718735e-05,
567
+ "loss": 0.7829,
568
+ "step": 92000
569
+ },
570
+ {
571
+ "epoch": 59.01,
572
+ "learning_rate": 5.985585137257401e-05,
573
+ "loss": 0.7043,
574
+ "step": 93000
575
+ },
576
+ {
577
+ "epoch": 60.0,
578
+ "learning_rate": 5.90440267166055e-05,
579
+ "loss": 0.7318,
580
+ "step": 94000
581
+ },
582
+ {
583
+ "epoch": 60.01,
584
+ "learning_rate": 5.8229729514036705e-05,
585
+ "loss": 0.7595,
586
+ "step": 95000
587
+ },
588
+ {
589
+ "epoch": 61.0,
590
+ "learning_rate": 5.74131823855921e-05,
591
+ "loss": 0.6896,
592
+ "step": 96000
593
+ },
594
+ {
595
+ "epoch": 62.0,
596
+ "learning_rate": 5.6594608567103456e-05,
597
+ "loss": 0.7431,
598
+ "step": 97000
599
+ },
600
+ {
601
+ "epoch": 62.01,
602
+ "learning_rate": 5.577423184847932e-05,
603
+ "loss": 0.7372,
604
+ "step": 98000
605
+ },
606
+ {
607
+ "epoch": 63.0,
608
+ "learning_rate": 5.495227651252315e-05,
609
+ "loss": 0.6896,
610
+ "step": 99000
611
+ },
612
+ {
613
+ "epoch": 64.0,
614
+ "learning_rate": 5.4128967273616625e-05,
615
+ "loss": 0.7612,
616
+ "step": 100000
617
+ },
618
+ {
619
+ "epoch": 64.0,
620
+ "eval_loss": 0.4362615644931793,
621
+ "eval_runtime": 10.4425,
622
+ "eval_samples_per_second": 478.814,
623
+ "eval_steps_per_second": 3.831,
624
+ "step": 100000
625
  }
626
  ],
627
  "max_steps": 200000,
628
  "num_train_epochs": 9223372036854775807,
629
+ "total_flos": 1.6848093869600932e+18,
630
  "trial_name": null,
631
  "trial_params": null
632
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f22933984e7fa2ac0e3974e919f9b0f04b81f66db9c9cf35e614e54253d9183c
3
  size 442675755
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf3179e77f86e938834ad7a2cb0522bcd0f4403c0978f2db3b2fa245ace152d8
3
  size 442675755
runs/Feb06_00-07-44_t1v-n-d1a73e20-w-0/events.out.tfevents.1675642083.t1v-n-d1a73e20-w-0.22435.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ec9d64a7085bda55534125acb9dc2acbb166f6b59f9f34db70f6bd551c7ae36
3
- size 12013
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b913104c9e674fc5e3ac87efbab849f2f0ebd340712de4c306cd9be445b5130d
3
+ size 20289