smilemikan
commited on
Commit
•
e4d5b47
1
Parent(s):
2b16b0a
Training in progress, step 24500, 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:ab903c388a1316163f4c03985bea2aa1bccabb2de83e5d099e543d53a2a4bd24
|
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 sha256:9fcf27d360f555aee57f4cdd3f1b0117db4d32aa1f3f4cffcef63905b29447cf
|
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:a98fe984610d3154ad7e1626295fddc4cc07a279f045d7f058d9da9fb0fe198e
|
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:f5f8b99c7d953fa43770dbc516acb083b7e689c52db9836fe30479d24d71cfa1
|
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": 5.
|
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,
|
@@ -679,13 +679,27 @@
|
|
679 |
"eval_samples_per_second": 188.861,
|
680 |
"eval_steps_per_second": 11.817,
|
681 |
"step": 24000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
682 |
}
|
683 |
],
|
684 |
"logging_steps": 500,
|
685 |
"max_steps": 60000,
|
686 |
"num_train_epochs": 14,
|
687 |
"save_steps": 500,
|
688 |
-
"total_flos": 2.
|
689 |
"trial_name": null,
|
690 |
"trial_params": null
|
691 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4372690916061401,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-24500",
|
4 |
+
"epoch": 5.397664683851069,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 24500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
679 |
"eval_samples_per_second": 188.861,
|
680 |
"eval_steps_per_second": 11.817,
|
681 |
"step": 24000
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 5.4,
|
685 |
+
"learning_rate": 1.1836333333333334e-05,
|
686 |
+
"loss": 1.3484,
|
687 |
+
"step": 24500
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 5.4,
|
691 |
+
"eval_loss": 1.4372690916061401,
|
692 |
+
"eval_runtime": 45.4091,
|
693 |
+
"eval_samples_per_second": 199.916,
|
694 |
+
"eval_steps_per_second": 12.508,
|
695 |
+
"step": 24500
|
696 |
}
|
697 |
],
|
698 |
"logging_steps": 500,
|
699 |
"max_steps": 60000,
|
700 |
"num_train_epochs": 14,
|
701 |
"save_steps": 500,
|
702 |
+
"total_flos": 2.487026805099725e+16,
|
703 |
"trial_name": null,
|
704 |
"trial_params": null
|
705 |
}
|