t5-small-finetuned-breton-plus-cy-kw-4
This model is a fine-tuned version of Jendersen/t5-small-finetuned-breton-plus-cy-kw-4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2100
- Rouge1: 29.1335
- Rouge2: 14.3637
- Rougel: 27.0356
- Rougelsum: 27.1532
- Bleu: 0.0219
- Chrf++: 15.5355
- F1: 38.2823
- Gen Len: 18.3072
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 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Chrf++ | F1 | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.2271 | 1.0 | 4411 | 1.2206 | 29.0171 | 14.2599 | 26.9112 | 27.0261 | 0.0215 | 15.468 | 38.2012 | 18.3093 |
| 1.2388 | 2.0 | 8822 | 1.2156 | 29.0388 | 14.2927 | 26.9398 | 27.0536 | 0.0217 | 15.5068 | 38.2398 | 18.3039 |
| 1.2388 | 3.0 | 13233 | 1.2105 | 29.0866 | 14.322 | 26.9736 | 27.0891 | 0.0218 | 15.5128 | 38.2656 | 18.3065 |
| 1.2477 | 4.0 | 17644 | 1.2100 | 29.1335 | 14.3637 | 27.0356 | 27.1532 | 0.0219 | 15.5355 | 38.2823 | 18.3072 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2