stefania-radu
commited on
Commit
•
c134cc3
1
Parent(s):
1625a53
Training in progress, step 70000
Browse files- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +77 -3
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +1 -1
- training_args.bin +2 -2
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:febd4ddd93771c4f15dcf974f5893b102541ab530165ff6539605cf0e37dfc55
|
3 |
+
size 893441530
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e35925eb08957bf9a46de58b0202e620c1dd065067603389209eb33e48dd1166
|
3 |
size 454197066
|
last-checkpoint/rng_state.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 sha256:8998e548c91f0f182806a61c3bafac5235a976f6ff7eb69017a5b8e22c368c89
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:613de0658f4e0e57fee5c3fe331af891a766b9d5b43031df1917116c932b0b1d
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
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": 108.578,
|
451 |
"eval_steps_per_second": 13.572,
|
452 |
"step": 60000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
453 |
}
|
454 |
],
|
455 |
"max_steps": 1000000,
|
456 |
"num_train_epochs": 9223372036854775807,
|
457 |
-
"total_flos":
|
458 |
"trial_name": null,
|
459 |
"trial_params": null
|
460 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.07,
|
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": 108.578,
|
451 |
"eval_steps_per_second": 13.572,
|
452 |
"step": 60000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.06,
|
456 |
+
"learning_rate": 1.8747105736439825e-05,
|
457 |
+
"loss": 0.4672,
|
458 |
+
"step": 61000
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.06,
|
462 |
+
"learning_rate": 1.8746555659365244e-05,
|
463 |
+
"loss": 0.4634,
|
464 |
+
"step": 62000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.06,
|
468 |
+
"learning_rate": 1.8745957775658352e-05,
|
469 |
+
"loss": 0.4605,
|
470 |
+
"step": 63000
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.06,
|
474 |
+
"learning_rate": 1.8745312091857516e-05,
|
475 |
+
"loss": 0.4554,
|
476 |
+
"step": 64000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.07,
|
480 |
+
"learning_rate": 1.8744618615023832e-05,
|
481 |
+
"loss": 0.4539,
|
482 |
+
"step": 65000
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.07,
|
486 |
+
"eval_runtime": 3195.2405,
|
487 |
+
"eval_samples_per_second": 106.299,
|
488 |
+
"eval_steps_per_second": 13.288,
|
489 |
+
"step": 65000
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.07,
|
493 |
+
"learning_rate": 1.874387735274105e-05,
|
494 |
+
"loss": 0.4547,
|
495 |
+
"step": 66000
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.07,
|
499 |
+
"learning_rate": 1.8743088313115487e-05,
|
500 |
+
"loss": 0.4536,
|
501 |
+
"step": 67000
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.07,
|
505 |
+
"learning_rate": 1.8742251504775967e-05,
|
506 |
+
"loss": 0.4548,
|
507 |
+
"step": 68000
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.07,
|
511 |
+
"learning_rate": 1.8741366936873687e-05,
|
512 |
+
"loss": 0.4528,
|
513 |
+
"step": 69000
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.07,
|
517 |
+
"learning_rate": 1.8740434619082138e-05,
|
518 |
+
"loss": 0.4525,
|
519 |
+
"step": 70000
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.07,
|
523 |
+
"eval_runtime": 2998.8361,
|
524 |
+
"eval_samples_per_second": 113.261,
|
525 |
+
"eval_steps_per_second": 14.158,
|
526 |
+
"step": 70000
|
527 |
}
|
528 |
],
|
529 |
"max_steps": 1000000,
|
530 |
"num_train_epochs": 9223372036854775807,
|
531 |
+
"total_flos": 6.198227121261773e+20,
|
532 |
"trial_name": null,
|
533 |
"trial_params": null
|
534 |
}
|
last-checkpoint/training_args.bin
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 sha256:3314aeda295ada0bfe55795dcf769542363573771d9b1416041c426b80bcfe0f
|
3 |
+
size 3768
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 454197066
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e35925eb08957bf9a46de58b0202e620c1dd065067603389209eb33e48dd1166
|
3 |
size 454197066
|
training_args.bin
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 sha256:3314aeda295ada0bfe55795dcf769542363573771d9b1416041c426b80bcfe0f
|
3 |
+
size 3768
|