metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: opus-mt-ru-en-finetuned
results: []
opus-mt-ru-en-finetuned
This model is a fine-tuned version of kazandaev/opus-mt-ru-en-finetuned on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0396
- Bleu: 43.4662
- Gen Len: 26.1749
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 |
|---|---|---|---|---|---|
| 0.7849 | 1.0 | 35147 | 1.0571 | 42.596 | 26.1388 |
| 0.7868 | 2.0 | 70294 | 1.0529 | 42.8209 | 26.1962 |
| 0.7815 | 3.0 | 105441 | 1.0493 | 43.0675 | 26.1079 |
| 0.7835 | 4.0 | 140588 | 1.0474 | 42.9025 | 26.1529 |
| 0.7859 | 5.0 | 175735 | 1.0473 | 43.2471 | 26.1164 |
| 0.7935 | 6.0 | 210882 | 1.0453 | 43.2605 | 26.1132 |
| 0.8058 | 7.0 | 246029 | 1.0443 | 43.1831 | 26.1057 |
| 0.8118 | 8.0 | 281176 | 1.0419 | 43.432 | 26.127 |
| 0.8223 | 9.0 | 316323 | 1.0405 | 43.4938 | 26.181 |
| 0.8462 | 10.0 | 351470 | 1.0396 | 43.4662 | 26.1749 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0