t5-small-finetuned-breton-plus-cy-kw-2
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6534
- Rouge1: 15.7369
- Rouge2: 3.1754
- Rougel: 13.9102
- Rougelsum: 14.0207
- Bleu: 0.0054
- Chrf++: 7.1111
- F1: 25.6897
- Gen Len: 19.4503
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 3.4421 | 1.0 | 4411 | 3.0937 | 12.7344 | 1.9793 | 11.3477 | 11.4291 | 0.0034 | 5.7415 | 22.5453 | 19.5236 |
| 3.1226 | 2.0 | 8822 | 2.8109 | 14.6797 | 2.6606 | 12.9787 | 13.0713 | 0.0046 | 6.6393 | 24.3985 | 19.4969 |
| 2.9845 | 3.0 | 13233 | 2.6895 | 15.4935 | 3.0809 | 13.6935 | 13.8037 | 0.0052 | 6.9966 | 25.2989 | 19.4651 |
| 2.9469 | 4.0 | 17644 | 2.6534 | 15.7369 | 3.1754 | 13.9102 | 14.0207 | 0.0054 | 7.1111 | 25.6897 | 19.4503 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2