update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- bleu
|
7 |
+
model-index:
|
8 |
+
- name: opus-mt-en-ru-finetuned-en-to-ru-Legal
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# opus-mt-en-ru-finetuned-en-to-ru-Legal
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ru](https://huggingface.co/Helsinki-NLP/opus-mt-en-ru) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.8561
|
20 |
+
- Bleu: 46.7284
|
21 |
+
- Gen Len: 23.1317
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 16
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 10
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
52 |
+
| No log | 1.0 | 387 | 1.1719 | 34.0562 | 22.991 |
|
53 |
+
| 1.524 | 2.0 | 774 | 1.0342 | 37.7233 | 23.0052 |
|
54 |
+
| 1.0226 | 3.0 | 1161 | 0.9595 | 40.0983 | 22.9755 |
|
55 |
+
| 0.8066 | 4.0 | 1548 | 0.9188 | 41.9634 | 23.1162 |
|
56 |
+
| 0.8066 | 5.0 | 1935 | 0.8907 | 43.6537 | 23.0923 |
|
57 |
+
| 0.6637 | 6.0 | 2322 | 0.8771 | 44.5208 | 23.1097 |
|
58 |
+
| 0.5697 | 7.0 | 2709 | 0.8669 | 45.5589 | 23.1388 |
|
59 |
+
| 0.5175 | 8.0 | 3096 | 0.8603 | 46.2211 | 23.2356 |
|
60 |
+
| 0.5175 | 9.0 | 3483 | 0.8566 | 46.7201 | 23.1375 |
|
61 |
+
| 0.4768 | 10.0 | 3870 | 0.8561 | 46.7284 | 23.1317 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.13.0
|
67 |
+
- Pytorch 1.12.0
|
68 |
+
- Datasets 2.4.0
|
69 |
+
- Tokenizers 0.10.3
|