smilemikan
commited on
Commit
•
1384324
1
Parent(s):
ce07a6a
Training in progress, step 17500, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5125261
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b769b963079720399bddcf8f6713eb4f0ccae41546917240896f767e067fd97
|
3 |
size 5125261
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2460465086
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86411b0eb06b2a940a0ba6fd89a46289fa982e96af14690b8a45cfae4fe0ebbd
|
3 |
size 2460465086
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce02e0f280ae812f660d3304d512201620a85f7cf68fde2ecd2498750093e2d3
|
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 sha256:8ef6353bbbc8c448898893d32d6996e6a0eb823f2ea7b5f853d375c80881815f
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-
|
4 |
-
"epoch": 3.
|
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,
|
@@ -483,13 +483,27 @@
|
|
483 |
"eval_samples_per_second": 209.168,
|
484 |
"eval_steps_per_second": 13.087,
|
485 |
"step": 17000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
486 |
}
|
487 |
],
|
488 |
"logging_steps": 500,
|
489 |
"max_steps": 60000,
|
490 |
"num_train_epochs": 14,
|
491 |
"save_steps": 500,
|
492 |
-
"total_flos": 1.
|
493 |
"trial_name": null,
|
494 |
"trial_params": null
|
495 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.5335613489151,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-17500",
|
4 |
+
"epoch": 3.855474774179335,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 17500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
483 |
"eval_samples_per_second": 209.168,
|
484 |
"eval_steps_per_second": 13.087,
|
485 |
"step": 17000
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 3.86,
|
489 |
+
"learning_rate": 1.4169000000000001e-05,
|
490 |
+
"loss": 1.5173,
|
491 |
+
"step": 17500
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 3.86,
|
495 |
+
"eval_loss": 1.5335613489151,
|
496 |
+
"eval_runtime": 43.512,
|
497 |
+
"eval_samples_per_second": 208.632,
|
498 |
+
"eval_steps_per_second": 13.054,
|
499 |
+
"step": 17500
|
500 |
}
|
501 |
],
|
502 |
"logging_steps": 500,
|
503 |
"max_steps": 60000,
|
504 |
"num_train_epochs": 14,
|
505 |
"save_steps": 500,
|
506 |
+
"total_flos": 1.7759219048251392e+16,
|
507 |
"trial_name": null,
|
508 |
"trial_params": null
|
509 |
}
|