t5small_enfr_opus
This model is a fine-tuned version of Mat17892/t5small_enfr_opus on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7526
- Bleu: 9.132
- Gen Len: 18.2648
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.8635 | 1.0 | 7500 | 0.7530 | 9.1424 | 18.2627 |
| 0.8555 | 2.0 | 15000 | 0.7526 | 9.132 | 18.2648 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3