Fine-tuned with 5000 samples mBART version mbart_v2
Browse files- README.md +5 -4
- generation_config.json +1 -0
README.md
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
@@ -12,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# e2m_translation_project
|
14 |
|
15 |
-
This model
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 0.
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -45,8 +46,8 @@ The following hyperparameters were used during training:
|
|
45 |
|
46 |
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
-
| 0.
|
49 |
-
| 0.
|
50 |
|
51 |
|
52 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
base_model: facebook/mbart-large-50-one-to-many-mmt
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# e2m_translation_project
|
15 |
|
16 |
+
This model is a fine-tuned version of [facebook/mbart-large-50-one-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-one-to-many-mmt) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.3881
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 0.4269 | 1.0 | 625 | 0.3894 |
|
50 |
+
| 0.2929 | 2.0 | 1250 | 0.3881 |
|
51 |
|
52 |
|
53 |
### Framework versions
|
generation_config.json
CHANGED
@@ -4,6 +4,7 @@
|
|
4 |
"decoder_start_token_id": 2,
|
5 |
"early_stopping": true,
|
6 |
"eos_token_id": 2,
|
|
|
7 |
"max_length": 200,
|
8 |
"num_beams": 5,
|
9 |
"pad_token_id": 1,
|
|
|
4 |
"decoder_start_token_id": 2,
|
5 |
"early_stopping": true,
|
6 |
"eos_token_id": 2,
|
7 |
+
"forced_eos_token_id": 2,
|
8 |
"max_length": 200,
|
9 |
"num_beams": 5,
|
10 |
"pad_token_id": 1,
|