t5-small-jfleg-grammar-correction
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6426
- Exact Match: 10.56
- Rougel: 77.57
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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | Rougel |
|---|---|---|---|---|---|
| 1.2408 | 1.0 | 76 | 0.9163 | 7.95 | 71.1 |
| 0.9395 | 2.0 | 152 | 0.8600 | 11.26 | 76.12 |
| 0.8515 | 3.0 | 228 | 0.8248 | 11.26 | 76.4 |
| 0.8638 | 4.0 | 304 | 0.8094 | 11.26 | 76.64 |
| 0.8257 | 5.0 | 380 | 0.8075 | 11.26 | 76.66 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1