en-lt-t5-small
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.8569
- Model Preparation Time: 0.0056
- Bleu: 1.799
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Bleu |
|---|---|---|---|---|---|
| No log | 1.0 | 250 | 3.2005 | 0.0056 | 2.0592 |
| 3.532 | 2.0 | 500 | 3.1012 | 0.0056 | 1.887 |
| 3.532 | 3.0 | 750 | 3.0342 | 0.0056 | 1.931 |
| 3.3132 | 4.0 | 1000 | 2.9828 | 0.0056 | 1.8851 |
| 3.3132 | 5.0 | 1250 | 2.9414 | 0.0056 | 1.8526 |
| 3.2165 | 6.0 | 1500 | 2.9097 | 0.0056 | 1.8195 |
| 3.2165 | 7.0 | 1750 | 2.8858 | 0.0056 | 1.8515 |
| 3.1562 | 8.0 | 2000 | 2.8698 | 0.0056 | 1.8003 |
| 3.1562 | 9.0 | 2250 | 2.8605 | 0.0056 | 1.7803 |
| 3.1312 | 10.0 | 2500 | 2.8569 | 0.0056 | 1.799 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3