metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: opus-mt-en-ru-finetuned
results: []
opus-mt-en-ru-finetuned
This model is a fine-tuned version of kazandaev/opus-mt-en-ru-finetuned on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7772
- Bleu: 40.4878
- Gen Len: 29.7466
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: 5e-06
- 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 |
|---|---|---|---|---|---|
| 0.7247 | 1.0 | 35147 | 0.7926 | 40.1369 | 29.7264 |
| 0.7336 | 2.0 | 70294 | 0.7913 | 40.242 | 29.737 |
| 0.7593 | 3.0 | 105441 | 0.7899 | 40.1589 | 29.7651 |
| 0.7547 | 4.0 | 140588 | 0.7871 | 40.3547 | 29.6178 |
| 0.7601 | 5.0 | 175735 | 0.7842 | 40.3533 | 29.7711 |
| 0.7671 | 6.0 | 210882 | 0.7831 | 40.4168 | 29.7175 |
| 0.7777 | 7.0 | 246029 | 0.7806 | 40.506 | 29.7661 |
| 0.7816 | 8.0 | 281176 | 0.7777 | 40.7829 | 29.6526 |
| 0.7961 | 9.0 | 316323 | 0.7775 | 40.4808 | 29.7885 |
| 0.8187 | 10.0 | 351470 | 0.7772 | 40.4878 | 29.7466 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0