|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: opus-mt-en-ru-finetuned |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# opus-mt-en-ru-finetuned |
|
|
|
This model is a fine-tuned version of [kazandaev/opus-mt-en-ru-finetuned](https://huggingface.co/kazandaev/opus-mt-en-ru-finetuned) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7867 |
|
- Bleu: 40.0684 |
|
- Gen Len: 29.6714 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1e-05 |
|
- train_batch_size: 49 |
|
- eval_batch_size: 24 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:| |
|
| 0.7728 | 1.0 | 35147 | 0.8184 | 38.866 | 30.0397 | |
|
| 0.779 | 2.0 | 70294 | 0.8131 | 39.1716 | 29.8013 | |
|
| 0.8029 | 3.0 | 105441 | 0.8097 | 39.0735 | 29.8549 | |
|
| 0.7938 | 4.0 | 140588 | 0.8050 | 39.4177 | 29.709 | |
|
| 0.7944 | 5.0 | 175735 | 0.8002 | 39.5476 | 29.7991 | |
|
| 0.7966 | 6.0 | 210882 | 0.7981 | 39.5658 | 29.808 | |
|
| 0.8016 | 7.0 | 246029 | 0.7932 | 39.8693 | 29.7747 | |
|
| 0.7997 | 8.0 | 281176 | 0.7874 | 40.0442 | 29.6934 | |
|
| 0.8083 | 9.0 | 316323 | 0.7875 | 40.0731 | 29.6948 | |
|
| 0.8248 | 10.0 | 351470 | 0.7867 | 40.0684 | 29.6714 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.16.2 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 1.18.3 |
|
- Tokenizers 0.11.0 |
|
|
