update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,28 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- wmt16
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: distilled-mt5-small-0.2-2
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -14,7 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# distilled-mt5-small-0.2-2
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the wmt16 dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- ro
|
| 5 |
license: apache-2.0
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- wmt16
|
| 10 |
+
metrics:
|
| 11 |
+
- bleu
|
| 12 |
model-index:
|
| 13 |
- name: distilled-mt5-small-0.2-2
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Translation
|
| 17 |
+
type: translation
|
| 18 |
+
dataset:
|
| 19 |
+
name: wmt16 ro-en
|
| 20 |
+
type: wmt16
|
| 21 |
+
args: ro-en
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Bleu
|
| 24 |
+
type: bleu
|
| 25 |
+
value: 1.7481
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
# distilled-mt5-small-0.2-2
|
| 32 |
|
| 33 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the wmt16 ro-en dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 3.5828
|
| 36 |
+
- Bleu: 1.7481
|
| 37 |
+
- Gen Len: 81.4652
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|