smilemikan
commited on
Commit
•
97785e3
1
Parent(s):
8976ebb
Training in progress, step 32500, 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 sha256:0081ae5e77211e743120a4c84ac3a18387e09708ecf93bdb1f658909df9bee96
|
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 sha256:41c9f0053f84b12d0a080f73168efbfe06e797aa62cc326ad36a147fcd845ab1
|
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:a9f2618f6bf64324bf1f1ce7b94a614bcdead23b8045cf87ce9f8f7a36eb50ad
|
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 sha256:347d7531d0795de8480e46c67fb96339fa7a09b095574f41bb3d3bb7e2cdec53
|
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,
|
@@ -903,13 +903,27 @@
|
|
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.
|
913 |
"trial_name": null,
|
914 |
"trial_params": null
|
915 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3801844120025635,
|
3 |
+
"best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-32500",
|
4 |
+
"epoch": 7.160167437761621,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 32500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
903 |
"eval_samples_per_second": 204.116,
|
904 |
"eval_steps_per_second": 12.771,
|
905 |
"step": 32000
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 7.16,
|
909 |
+
"learning_rate": 9.17e-06,
|
910 |
+
"loss": 1.2421,
|
911 |
+
"step": 32500
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 7.16,
|
915 |
+
"eval_loss": 1.3801844120025635,
|
916 |
+
"eval_runtime": 44.8621,
|
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": 3.2956141653590016e+16,
|
927 |
"trial_name": null,
|
928 |
"trial_params": null
|
929 |
}
|