smilemikan
commited on
Commit
•
8ddaa29
1
Parent(s):
cdc6d10
Training in progress, step 32000, 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 sha256:77c08ec04c71763a007d93f238ab1345d2e8b25f075c9781d56b06b8155e1a7a
|
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 sha256:8cfd74414906ebf7bf78a0daa45891ad2cea1772666f0ac2cf53c35c8ab985c7
|
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:adafc02eabbd967db9e0bce807d2ee01b2cd1d5e66feb95cd1b8351fa61e83c1
|
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 sha256:96ed6dc9d453900f914b6fd87293f6beab4240ad1a276e1ad8d0ee8fe48e9169
|
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 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -889,13 +889,27 @@
|
|
889 |
"eval_samples_per_second": 202.021,
|
890 |
"eval_steps_per_second": 12.64,
|
891 |
"step": 31500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
892 |
}
|
893 |
],
|
894 |
"logging_steps": 500,
|
895 |
"max_steps": 60000,
|
896 |
"num_train_epochs": 14,
|
897 |
"save_steps": 500,
|
898 |
-
"total_flos": 3.
|
899 |
"trial_name": null,
|
900 |
"trial_params": null
|
901 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3853869438171387,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-32000",
|
4 |
+
"epoch": 7.0500110156422116,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 32000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
889 |
"eval_samples_per_second": 202.021,
|
890 |
"eval_steps_per_second": 12.64,
|
891 |
"step": 31500
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 7.05,
|
895 |
+
"learning_rate": 9.336666666666666e-06,
|
896 |
+
"loss": 1.2419,
|
897 |
+
"step": 32000
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 7.05,
|
901 |
+
"eval_loss": 1.3853869438171387,
|
902 |
+
"eval_runtime": 44.4747,
|
903 |
+
"eval_samples_per_second": 204.116,
|
904 |
+
"eval_steps_per_second": 12.771,
|
905 |
+
"step": 32000
|
906 |
}
|
907 |
],
|
908 |
"logging_steps": 500,
|
909 |
"max_steps": 60000,
|
910 |
"num_train_epochs": 14,
|
911 |
"save_steps": 500,
|
912 |
+
"total_flos": 3.244954709183693e+16,
|
913 |
"trial_name": null,
|
914 |
"trial_params": null
|
915 |
}
|