t5-small-translate-en-pg
This model is a fine-tuned version of google-t5/t5-small on JstnMcBrd/wikipedia-1M-en-pg. It achieves the following results on the evaluation set:
- Loss: 1.3305
Model description
This model has been fine-tuned to translate between English and Pig Latin.
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: 32
- eval_batch_size: 32
- 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: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8312 | 1.0 | 10000 | 1.6410 |
| 1.6099 | 2.0 | 20000 | 1.4790 |
| 1.4995 | 3.0 | 30000 | 1.4114 |
| 1.4428 | 4.0 | 40000 | 1.3751 |
| 1.4152 | 5.0 | 50000 | 1.3526 |
| 1.4103 | 6.0 | 60000 | 1.3397 |
| 1.3846 | 7.0 | 70000 | 1.3328 |
| 1.38 | 8.0 | 80000 | 1.3305 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1