results50000f
This model is a fine-tuned version of t5-small on the wmt16 dataset. It achieves the following results on the evaluation set:
- Loss: 1.9250
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7357 | 1.0 | 3125 | 2.0753 |
| 2.5874 | 2.0 | 6250 | 2.0158 |
| 2.5294 | 3.0 | 9375 | 1.9860 |
| 2.4908 | 4.0 | 12500 | 1.9678 |
| 2.4653 | 5.0 | 15625 | 1.9529 |
| 2.4468 | 6.0 | 18750 | 1.9422 |
| 2.4298 | 7.0 | 21875 | 1.9334 |
| 2.4213 | 8.0 | 25000 | 1.9288 |
| 2.4136 | 9.0 | 28125 | 1.9264 |
| 2.409 | 10.0 | 31250 | 1.9250 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3