End of training
Browse files- README.md +3 -1
- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
base_model: UBC-NLP/AraT5v2-base-1024
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: T5-MSAizer-full
|
7 |
results: []
|
@@ -12,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# T5-MSAizer-full
|
14 |
|
15 |
-
This model is a fine-tuned version of [UBC-NLP/AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) on
|
16 |
|
17 |
## Model description
|
18 |
|
|
|
2 |
base_model: UBC-NLP/AraT5v2-base-1024
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- Murhaf/dialect_msa_silver_parallel
|
7 |
model-index:
|
8 |
- name: T5-MSAizer-full
|
9 |
results: []
|
|
|
14 |
|
15 |
# T5-MSAizer-full
|
16 |
|
17 |
+
This model is a fine-tuned version of [UBC-NLP/AraT5v2-base-1024](https://huggingface.co/UBC-NLP/AraT5v2-base-1024) on the Murhaf/dialect_msa_silver_parallel dataset.
|
18 |
|
19 |
## Model description
|
20 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_samples": 1,
|
4 |
+
"eval_train_bleu": 0.23015055592689426,
|
5 |
+
"eval_train_loss": 2.091299533843994,
|
6 |
+
"eval_train_runtime": 24.4061,
|
7 |
+
"eval_train_samples_per_second": 41.014,
|
8 |
+
"eval_train_steps_per_second": 1.311,
|
9 |
+
"train_loss": 1.662468353180182,
|
10 |
+
"train_runtime": 7285.6469,
|
11 |
+
"train_samples": 700386,
|
12 |
+
"train_samples_per_second": 96.132,
|
13 |
+
"train_steps_per_second": 3.004
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_samples": 1,
|
4 |
+
"eval_train_bleu": 0.23015055592689426,
|
5 |
+
"eval_train_loss": 2.091299533843994,
|
6 |
+
"eval_train_runtime": 24.4061,
|
7 |
+
"eval_train_samples_per_second": 41.014,
|
8 |
+
"eval_train_steps_per_second": 1.311
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.662468353180182,
|
4 |
+
"train_runtime": 7285.6469,
|
5 |
+
"train_samples": 700386,
|
6 |
+
"train_samples_per_second": 96.132,
|
7 |
+
"train_steps_per_second": 3.004
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|