sekarmulyani
commited on
Commit
•
20402e0
1
Parent(s):
0b29a23
Upload 11 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +3 -193
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 884664069
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d93e699da71d0862faff7ea11e941320c096aa97e2704a4dcb8db8451b403be3
|
3 |
size 884664069
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 442316593
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a300b6e00b389cf906d17bd5afa09cb757f33bdab03f07cabb35a93260c354a3
|
3 |
size 442316593
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4f0d2ea3c2ec79cb078a4d94380d9da3e21245c06539472c4b32fd7f0898d96
|
3 |
size 14575
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b71634c2199304e1d7a17effc61cbe89290f24881dcc6b00af4a5ebf910d9dd8
|
3 |
size 627
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.49651709628372404,
|
3 |
"best_model_checkpoint": "./indobertweet-review-rating/checkpoint-28596",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -393,203 +393,13 @@
|
|
393 |
"eval_samples_per_second": 58.879,
|
394 |
"eval_steps_per_second": 7.362,
|
395 |
"step": 28596
|
396 |
-
},
|
397 |
-
{
|
398 |
-
"epoch": 4.06,
|
399 |
-
"learning_rate": 9.858721499510422e-06,
|
400 |
-
"loss": 0.2317,
|
401 |
-
"step": 29000
|
402 |
-
},
|
403 |
-
{
|
404 |
-
"epoch": 4.13,
|
405 |
-
"learning_rate": 9.683871870191636e-06,
|
406 |
-
"loss": 0.2289,
|
407 |
-
"step": 29500
|
408 |
-
},
|
409 |
-
{
|
410 |
-
"epoch": 4.2,
|
411 |
-
"learning_rate": 9.50902224087285e-06,
|
412 |
-
"loss": 0.2273,
|
413 |
-
"step": 30000
|
414 |
-
},
|
415 |
-
{
|
416 |
-
"epoch": 4.27,
|
417 |
-
"learning_rate": 9.334172611554064e-06,
|
418 |
-
"loss": 0.2344,
|
419 |
-
"step": 30500
|
420 |
-
},
|
421 |
-
{
|
422 |
-
"epoch": 4.34,
|
423 |
-
"learning_rate": 9.159322982235278e-06,
|
424 |
-
"loss": 0.2256,
|
425 |
-
"step": 31000
|
426 |
-
},
|
427 |
-
{
|
428 |
-
"epoch": 4.41,
|
429 |
-
"learning_rate": 8.984473352916492e-06,
|
430 |
-
"loss": 0.2265,
|
431 |
-
"step": 31500
|
432 |
-
},
|
433 |
-
{
|
434 |
-
"epoch": 4.48,
|
435 |
-
"learning_rate": 8.809623723597706e-06,
|
436 |
-
"loss": 0.2274,
|
437 |
-
"step": 32000
|
438 |
-
},
|
439 |
-
{
|
440 |
-
"epoch": 4.55,
|
441 |
-
"learning_rate": 8.63477409427892e-06,
|
442 |
-
"loss": 0.2315,
|
443 |
-
"step": 32500
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 4.62,
|
447 |
-
"learning_rate": 8.459924464960135e-06,
|
448 |
-
"loss": 0.2231,
|
449 |
-
"step": 33000
|
450 |
-
},
|
451 |
-
{
|
452 |
-
"epoch": 4.69,
|
453 |
-
"learning_rate": 8.285074835641349e-06,
|
454 |
-
"loss": 0.233,
|
455 |
-
"step": 33500
|
456 |
-
},
|
457 |
-
{
|
458 |
-
"epoch": 4.76,
|
459 |
-
"learning_rate": 8.110225206322563e-06,
|
460 |
-
"loss": 0.234,
|
461 |
-
"step": 34000
|
462 |
-
},
|
463 |
-
{
|
464 |
-
"epoch": 4.83,
|
465 |
-
"learning_rate": 7.935375577003777e-06,
|
466 |
-
"loss": 0.2237,
|
467 |
-
"step": 34500
|
468 |
-
},
|
469 |
-
{
|
470 |
-
"epoch": 4.9,
|
471 |
-
"learning_rate": 7.760525947684991e-06,
|
472 |
-
"loss": 0.2316,
|
473 |
-
"step": 35000
|
474 |
-
},
|
475 |
-
{
|
476 |
-
"epoch": 4.97,
|
477 |
-
"learning_rate": 7.585676318366205e-06,
|
478 |
-
"loss": 0.2223,
|
479 |
-
"step": 35500
|
480 |
-
},
|
481 |
-
{
|
482 |
-
"epoch": 5.0,
|
483 |
-
"eval_akurasi": 0.46829716084191203,
|
484 |
-
"eval_f1": 0.49530800928009977,
|
485 |
-
"eval_loss": 0.47835299372673035,
|
486 |
-
"eval_roc_auc": 0.6813979411186152,
|
487 |
-
"eval_runtime": 258.995,
|
488 |
-
"eval_samples_per_second": 58.885,
|
489 |
-
"eval_steps_per_second": 7.363,
|
490 |
-
"step": 35745
|
491 |
-
},
|
492 |
-
{
|
493 |
-
"epoch": 5.04,
|
494 |
-
"learning_rate": 7.41082668904742e-06,
|
495 |
-
"loss": 0.2077,
|
496 |
-
"step": 36000
|
497 |
-
},
|
498 |
-
{
|
499 |
-
"epoch": 5.11,
|
500 |
-
"learning_rate": 7.2359770597286336e-06,
|
501 |
-
"loss": 0.1861,
|
502 |
-
"step": 36500
|
503 |
-
},
|
504 |
-
{
|
505 |
-
"epoch": 5.18,
|
506 |
-
"learning_rate": 7.061127430409848e-06,
|
507 |
-
"loss": 0.1971,
|
508 |
-
"step": 37000
|
509 |
-
},
|
510 |
-
{
|
511 |
-
"epoch": 5.25,
|
512 |
-
"learning_rate": 6.886277801091063e-06,
|
513 |
-
"loss": 0.196,
|
514 |
-
"step": 37500
|
515 |
-
},
|
516 |
-
{
|
517 |
-
"epoch": 5.32,
|
518 |
-
"learning_rate": 6.711428171772276e-06,
|
519 |
-
"loss": 0.1908,
|
520 |
-
"step": 38000
|
521 |
-
},
|
522 |
-
{
|
523 |
-
"epoch": 5.39,
|
524 |
-
"learning_rate": 6.53657854245349e-06,
|
525 |
-
"loss": 0.1911,
|
526 |
-
"step": 38500
|
527 |
-
},
|
528 |
-
{
|
529 |
-
"epoch": 5.46,
|
530 |
-
"learning_rate": 6.361728913134705e-06,
|
531 |
-
"loss": 0.1903,
|
532 |
-
"step": 39000
|
533 |
-
},
|
534 |
-
{
|
535 |
-
"epoch": 5.53,
|
536 |
-
"learning_rate": 6.186879283815918e-06,
|
537 |
-
"loss": 0.1976,
|
538 |
-
"step": 39500
|
539 |
-
},
|
540 |
-
{
|
541 |
-
"epoch": 5.6,
|
542 |
-
"learning_rate": 6.012029654497133e-06,
|
543 |
-
"loss": 0.1971,
|
544 |
-
"step": 40000
|
545 |
-
},
|
546 |
-
{
|
547 |
-
"epoch": 5.67,
|
548 |
-
"learning_rate": 5.8371800251783475e-06,
|
549 |
-
"loss": 0.1928,
|
550 |
-
"step": 40500
|
551 |
-
},
|
552 |
-
{
|
553 |
-
"epoch": 5.74,
|
554 |
-
"learning_rate": 5.662330395859561e-06,
|
555 |
-
"loss": 0.1927,
|
556 |
-
"step": 41000
|
557 |
-
},
|
558 |
-
{
|
559 |
-
"epoch": 5.81,
|
560 |
-
"learning_rate": 5.487480766540776e-06,
|
561 |
-
"loss": 0.1917,
|
562 |
-
"step": 41500
|
563 |
-
},
|
564 |
-
{
|
565 |
-
"epoch": 5.87,
|
566 |
-
"learning_rate": 5.31263113722199e-06,
|
567 |
-
"loss": 0.2022,
|
568 |
-
"step": 42000
|
569 |
-
},
|
570 |
-
{
|
571 |
-
"epoch": 5.94,
|
572 |
-
"learning_rate": 5.137781507903203e-06,
|
573 |
-
"loss": 0.1988,
|
574 |
-
"step": 42500
|
575 |
-
},
|
576 |
-
{
|
577 |
-
"epoch": 6.0,
|
578 |
-
"eval_akurasi": 0.4731493016851354,
|
579 |
-
"eval_f1": 0.496174038362557,
|
580 |
-
"eval_loss": 0.5363304018974304,
|
581 |
-
"eval_roc_auc": 0.6824306602845714,
|
582 |
-
"eval_runtime": 259.1769,
|
583 |
-
"eval_samples_per_second": 58.844,
|
584 |
-
"eval_steps_per_second": 7.358,
|
585 |
-
"step": 42894
|
586 |
}
|
587 |
],
|
588 |
"logging_steps": 500,
|
589 |
"max_steps": 57192,
|
590 |
"num_train_epochs": 8,
|
591 |
"save_steps": 500,
|
592 |
-
"total_flos":
|
593 |
"trial_name": null,
|
594 |
"trial_params": null
|
595 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.49651709628372404,
|
3 |
"best_model_checkpoint": "./indobertweet-review-rating/checkpoint-28596",
|
4 |
+
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 28596,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
393 |
"eval_samples_per_second": 58.879,
|
394 |
"eval_steps_per_second": 7.362,
|
395 |
"step": 28596
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
396 |
}
|
397 |
],
|
398 |
"logging_steps": 500,
|
399 |
"max_steps": 57192,
|
400 |
"num_train_epochs": 8,
|
401 |
"save_steps": 500,
|
402 |
+
"total_flos": 4.514475841140326e+16,
|
403 |
"trial_name": null,
|
404 |
"trial_params": null
|
405 |
}
|