Training in progress, step 70000
Browse files- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +2 -2
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +2 -2
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +77 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0d611070fc96c13fe2a726a75aa89fbb18b267a55a563cdceaf1c3fbade3f8c
|
3 |
+
size 893439185
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26811078f796ab6f92af5a3940b414f53cb4f1a1f7777c0f34bdde158fb49f0e
|
3 |
size 449471589
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff190ea62daf1e533d229f2cbdc2bf1b0b91f1b54ad94055b49d136687089c2b
|
3 |
+
size 14439
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40b1051d2935e5a6ad2bc776aeb5c7effef95653590b063d7af64113e86e7198
|
3 |
size 14503
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca733adc62d3884a07b0f3bff0700e4d418d28a780a35e3db8b9f7f1147beb15
|
3 |
+
size 14503
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f9ae59fc5fa85627e7d16c864bbec928ea1cdb8c2fa89705bb65d8bdd8ab7fb
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7c802ff93fc9d67d63f3e03f7bd5fd1c7e4a71a3faef71bb4d686a1c5885c38
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -450,11 +450,85 @@
|
|
450 |
"eval_samples_per_second": 813.826,
|
451 |
"eval_steps_per_second": 13.021,
|
452 |
"step": 60000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
453 |
}
|
454 |
],
|
455 |
"max_steps": 1000000,
|
456 |
"num_train_epochs": 16,
|
457 |
-
"total_flos": 4.
|
458 |
"trial_name": null,
|
459 |
"trial_params": null
|
460 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0689144410340983,
|
5 |
+
"global_step": 70000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
450 |
"eval_samples_per_second": 813.826,
|
451 |
"eval_steps_per_second": 13.021,
|
452 |
"step": 60000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.93,
|
456 |
+
"learning_rate": 0.00014995369178303722,
|
457 |
+
"loss": 0.4408,
|
458 |
+
"step": 61000
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.95,
|
462 |
+
"learning_rate": 0.0001499448905498439,
|
463 |
+
"loss": 0.4381,
|
464 |
+
"step": 62000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.96,
|
468 |
+
"learning_rate": 0.00014993532441053364,
|
469 |
+
"loss": 0.434,
|
470 |
+
"step": 63000
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.98,
|
474 |
+
"learning_rate": 0.0001499249934697203,
|
475 |
+
"loss": 0.4316,
|
476 |
+
"step": 64000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.99,
|
480 |
+
"learning_rate": 0.0001499138978403813,
|
481 |
+
"loss": 0.4275,
|
482 |
+
"step": 65000
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.99,
|
486 |
+
"eval_runtime": 1.0345,
|
487 |
+
"eval_samples_per_second": 966.655,
|
488 |
+
"eval_steps_per_second": 15.466,
|
489 |
+
"step": 65000
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.01,
|
493 |
+
"learning_rate": 0.00014990203764385677,
|
494 |
+
"loss": 0.425,
|
495 |
+
"step": 66000
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 1.02,
|
499 |
+
"learning_rate": 0.00014988941300984784,
|
500 |
+
"loss": 0.422,
|
501 |
+
"step": 67000
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 1.04,
|
505 |
+
"learning_rate": 0.0001498760240764155,
|
506 |
+
"loss": 0.4191,
|
507 |
+
"step": 68000
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.05,
|
511 |
+
"learning_rate": 0.000149861870989979,
|
512 |
+
"loss": 0.4164,
|
513 |
+
"step": 69000
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.07,
|
517 |
+
"learning_rate": 0.0001498469539053142,
|
518 |
+
"loss": 0.4138,
|
519 |
+
"step": 70000
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 1.07,
|
523 |
+
"eval_runtime": 1.1341,
|
524 |
+
"eval_samples_per_second": 881.784,
|
525 |
+
"eval_steps_per_second": 14.109,
|
526 |
+
"step": 70000
|
527 |
}
|
528 |
],
|
529 |
"max_steps": 1000000,
|
530 |
"num_train_epochs": 16,
|
531 |
+
"total_flos": 4.907011701442813e+21,
|
532 |
"trial_name": null,
|
533 |
"trial_params": null
|
534 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26811078f796ab6f92af5a3940b414f53cb4f1a1f7777c0f34bdde158fb49f0e
|
3 |
size 449471589
|