smilemikan
commited on
Commit
•
fa9c910
1
Parent(s):
d9ec1f0
Training in progress, step 20000, 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 sha256:04b41db138ee8e198f9e2a7b0efd7791bc14180db542c590d7ce8a9f5babd6ef
|
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 sha256:870a2832da25c2f26b5846c3556adfe33aff26954baa3852c79ff72069a23fc8
|
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 sha256:5f6c3cb8c70b6e982e63c05f3abfa9ad5033f15f0d861edf82a1c29cf22cd8ef
|
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 sha256:09a8b2cb77693ed976ba1ef3c7f415f6782867c443fd911c21fd3a0d2839b5c1
|
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": 4.
|
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,
|
@@ -553,13 +553,27 @@
|
|
553 |
"eval_samples_per_second": 209.952,
|
554 |
"eval_steps_per_second": 13.136,
|
555 |
"step": 19500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
556 |
}
|
557 |
],
|
558 |
"logging_steps": 500,
|
559 |
"max_steps": 60000,
|
560 |
"num_train_epochs": 14,
|
561 |
"save_steps": 500,
|
562 |
-
"total_flos":
|
563 |
"trial_name": null,
|
564 |
"trial_params": null
|
565 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.495379090309143,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-20000",
|
4 |
+
"epoch": 4.406256884776383,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 20000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
553 |
"eval_samples_per_second": 209.952,
|
554 |
"eval_steps_per_second": 13.136,
|
555 |
"step": 19500
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 4.41,
|
559 |
+
"learning_rate": 1.3335666666666667e-05,
|
560 |
+
"loss": 1.4563,
|
561 |
+
"step": 20000
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 4.41,
|
565 |
+
"eval_loss": 1.495379090309143,
|
566 |
+
"eval_runtime": 43.6248,
|
567 |
+
"eval_samples_per_second": 208.093,
|
568 |
+
"eval_steps_per_second": 13.02,
|
569 |
+
"step": 20000
|
570 |
}
|
571 |
],
|
572 |
"logging_steps": 500,
|
573 |
"max_steps": 60000,
|
574 |
"num_train_epochs": 14,
|
575 |
"save_steps": 500,
|
576 |
+
"total_flos": 2.029327540931789e+16,
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|
579 |
}
|