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: 1.0485
- Bleu: 42.9524
- Gen Len: 26.1412
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 |
|---|---|---|---|---|---|
| 0.8396 | 1.0 | 35147 | 1.0827 | 41.4836 | 26.1402 |
| 0.837 | 2.0 | 70294 | 1.0735 | 41.8146 | 26.1647 |
| 0.8266 | 3.0 | 105441 | 1.0659 | 42.0086 | 26.1026 |
| 0.8242 | 4.0 | 140588 | 1.0624 | 42.1259 | 26.1515 |
| 0.822 | 5.0 | 175735 | 1.0620 | 42.3133 | 26.0898 |
| 0.8242 | 6.0 | 210882 | 1.0573 | 42.6048 | 26.0841 |
| 0.831 | 7.0 | 246029 | 1.0567 | 42.793 | 26.0749 |
| 0.8313 | 8.0 | 281176 | 1.0518 | 42.8092 | 26.138 |
| 0.8354 | 9.0 | 316323 | 1.0502 | 42.8207 | 26.154 |
| 0.8533 | 10.0 | 351470 | 1.0485 | 42.9524 | 26.1412 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0