t5-small-finetuned-bible-only-breton-plus-cy-kw
This model is a fine-tuned version of Jendersen/t5-small-finetuned-bible-only-breton-plus-cy-kw on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2054
- Rouge1: 26.8429
- Rouge2: 13.7504
- Rougel: 24.6693
- Rougelsum: 24.9635
- Bleu: 0.0153
- Chrf++: 14.2939
- F1: 37.4225
- Gen Len: 18.9729
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Chrf++ | F1 | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.3074 | 1.0 | 1363 | 1.2329 | 26.577 | 13.4633 | 24.3875 | 24.6882 | 0.0148 | 14.0722 | 37.2142 | 18.9725 |
| 1.3080 | 2.0 | 2726 | 1.2282 | 26.6033 | 13.5047 | 24.3962 | 24.7089 | 0.015 | 14.1283 | 37.2602 | 18.9725 |
| 1.3043 | 3.0 | 4089 | 1.2247 | 26.6959 | 13.5529 | 24.5142 | 24.7963 | 0.015 | 14.1729 | 37.3207 | 18.9712 |
| 1.2956 | 4.0 | 5452 | 1.2193 | 26.6816 | 13.5333 | 24.4769 | 24.776 | 0.0149 | 14.1387 | 37.2674 | 18.9714 |
| 1.2869 | 5.0 | 6815 | 1.2130 | 26.6705 | 13.5661 | 24.4899 | 24.7795 | 0.0151 | 14.1594 | 37.2657 | 18.9729 |
| 1.2823 | 6.0 | 8178 | 1.2112 | 26.7702 | 13.6496 | 24.5669 | 24.8536 | 0.0152 | 14.2257 | 37.3449 | 18.9721 |
| 1.2869 | 7.0 | 9541 | 1.2084 | 26.7492 | 13.6547 | 24.566 | 24.8592 | 0.0152 | 14.254 | 37.366 | 18.973 |
| 1.2835 | 8.0 | 10904 | 1.2070 | 26.8021 | 13.6947 | 24.6226 | 24.9065 | 0.0153 | 14.2656 | 37.3938 | 18.9719 |
| 1.2832 | 9.0 | 12267 | 1.2058 | 26.8151 | 13.7173 | 24.6311 | 24.9288 | 0.0153 | 14.2839 | 37.4154 | 18.9729 |
| 1.2871 | 10.0 | 13630 | 1.2054 | 26.8429 | 13.7504 | 24.6693 | 24.9635 | 0.0153 | 14.2939 | 37.4225 | 18.9729 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2