smilemikan
commited on
Commit
•
12bbceb
1
Parent(s):
43b7a46
Training in progress, step 33000, 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:d3d1f233b798d9c9e51c543176faf1192828b6b182b85ea67aa328040efd29e9
|
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 sha256:8e35881a85dc39feac2c61fa1ccc3eb15e55d715b042f124d67f30ccf56613f4
|
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 sha256:5f5bd2a6214c593f957e01d6669742ef40b4c8bb741a9bed8543be78a2820205
|
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:bbd08fb5177a3c17f1128b7893f858061e8e9a5f6de92c18f940b5186da92d94
|
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": 7.
|
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,
|
@@ -917,13 +917,27 @@
|
|
917 |
"eval_samples_per_second": 202.353,
|
918 |
"eval_steps_per_second": 12.661,
|
919 |
"step": 32500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
920 |
}
|
921 |
],
|
922 |
"logging_steps": 500,
|
923 |
"max_steps": 60000,
|
924 |
"num_train_epochs": 14,
|
925 |
"save_steps": 500,
|
926 |
-
"total_flos": 3.
|
927 |
"trial_name": null,
|
928 |
"trial_params": null
|
929 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.380096673965454,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-33000",
|
4 |
+
"epoch": 7.270323859881031,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 33000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
917 |
"eval_samples_per_second": 202.353,
|
918 |
"eval_steps_per_second": 12.661,
|
919 |
"step": 32500
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 7.27,
|
923 |
+
"learning_rate": 9.003333333333334e-06,
|
924 |
+
"loss": 1.2177,
|
925 |
+
"step": 33000
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 7.27,
|
929 |
+
"eval_loss": 1.380096673965454,
|
930 |
+
"eval_runtime": 45.1593,
|
931 |
+
"eval_samples_per_second": 201.022,
|
932 |
+
"eval_steps_per_second": 12.578,
|
933 |
+
"step": 33000
|
934 |
}
|
935 |
],
|
936 |
"logging_steps": 500,
|
937 |
"max_steps": 60000,
|
938 |
"num_train_epochs": 14,
|
939 |
"save_steps": 500,
|
940 |
+
"total_flos": 3.345108802810675e+16,
|
941 |
"trial_name": null,
|
942 |
"trial_params": null
|
943 |
}
|