Commit
·
c5fd878
1
Parent(s):
598f1f8
End of training
Browse files- README.md +6 -1
- all_results.json +6 -6
- predict_results.json +3 -3
- train_results.json +3 -3
- trainer_state.json +3 -3
README.md
CHANGED
@@ -1,8 +1,13 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: t5-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: filipinolingo_translation
|
8 |
results: []
|
@@ -13,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# filipinolingo_translation
|
15 |
|
16 |
-
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- tl
|
4 |
+
- war
|
5 |
license: apache-2.0
|
6 |
base_model: t5-small
|
7 |
tags:
|
8 |
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- youdiniplays/tl_war
|
11 |
model-index:
|
12 |
- name: filipinolingo_translation
|
13 |
results: []
|
|
|
18 |
|
19 |
# filipinolingo_translation
|
20 |
|
21 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the youdiniplays/tl_war dataset.
|
22 |
|
23 |
## Model description
|
24 |
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"predict_loss": 3.60825777053833,
|
4 |
-
"predict_runtime": 0.
|
5 |
"predict_samples": 173,
|
6 |
-
"predict_samples_per_second":
|
7 |
-
"predict_steps_per_second": 11.
|
8 |
"train_loss": 3.948578590570494,
|
9 |
-
"train_runtime": 11.
|
10 |
"train_samples": 688,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 10.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"predict_loss": 3.60825777053833,
|
4 |
+
"predict_runtime": 0.9478,
|
5 |
"predict_samples": 173,
|
6 |
+
"predict_samples_per_second": 182.52,
|
7 |
+
"predict_steps_per_second": 11.605,
|
8 |
"train_loss": 3.948578590570494,
|
9 |
+
"train_runtime": 11.8282,
|
10 |
"train_samples": 688,
|
11 |
+
"train_samples_per_second": 174.499,
|
12 |
+
"train_steps_per_second": 10.906
|
13 |
}
|
predict_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"predict_loss": 3.60825777053833,
|
3 |
-
"predict_runtime": 0.
|
4 |
"predict_samples": 173,
|
5 |
-
"predict_samples_per_second":
|
6 |
-
"predict_steps_per_second": 11.
|
7 |
}
|
|
|
1 |
{
|
2 |
"predict_loss": 3.60825777053833,
|
3 |
+
"predict_runtime": 0.9478,
|
4 |
"predict_samples": 173,
|
5 |
+
"predict_samples_per_second": 182.52,
|
6 |
+
"predict_steps_per_second": 11.605
|
7 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"train_loss": 3.948578590570494,
|
4 |
-
"train_runtime": 11.
|
5 |
"train_samples": 688,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 10.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"train_loss": 3.948578590570494,
|
4 |
+
"train_runtime": 11.8282,
|
5 |
"train_samples": 688,
|
6 |
+
"train_samples_per_second": 174.499,
|
7 |
+
"train_steps_per_second": 10.906
|
8 |
}
|
trainer_state.json
CHANGED
@@ -13,9 +13,9 @@
|
|
13 |
"step": 129,
|
14 |
"total_flos": 14413901856768.0,
|
15 |
"train_loss": 3.948578590570494,
|
16 |
-
"train_runtime": 11.
|
17 |
-
"train_samples_per_second":
|
18 |
-
"train_steps_per_second": 10.
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
|
|
13 |
"step": 129,
|
14 |
"total_flos": 14413901856768.0,
|
15 |
"train_loss": 3.948578590570494,
|
16 |
+
"train_runtime": 11.8282,
|
17 |
+
"train_samples_per_second": 174.499,
|
18 |
+
"train_steps_per_second": 10.906
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|