t5-small-finetuned-bible-only-welsh-plus-br-kw
This model is a fine-tuned version of Jendersen/t5-small-finetuned-bible-only-welsh-plus-br-kw on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2249
- Rouge1: 20.0505
- Rouge2: 8.3773
- Rougel: 18.6412
- Rougelsum: 18.7877
- Bleu: 0.0047
- Chrf++: 10.7391
- F1: 40.4696
- Gen Len: 18.9646
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: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Chrf++ | F1 | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.2297 | 1.0 | 1483 | 1.2435 | 19.9793 | 8.3723 | 18.5684 | 18.714 | 0.0047 | 10.7341 | 40.4666 | 18.9646 |
| 1.2289 | 2.0 | 2966 | 1.2390 | 20.0689 | 8.4154 | 18.6582 | 18.7964 | 0.0048 | 10.7717 | 40.5071 | 18.9636 |
| 1.2423 | 3.0 | 4449 | 1.2335 | 19.9902 | 8.3641 | 18.5801 | 18.7223 | 0.0047 | 10.7328 | 40.4668 | 18.9641 |
| 1.2405 | 4.0 | 5932 | 1.2297 | 20.0322 | 8.3621 | 18.5998 | 18.7542 | 0.0047 | 10.7338 | 40.4683 | 18.9641 |
| 1.2443 | 5.0 | 7415 | 1.2266 | 19.996 | 8.3784 | 18.6022 | 18.7454 | 0.0047 | 10.7391 | 40.4632 | 18.9646 |
| 1.2620 | 6.0 | 8898 | 1.2249 | 20.0505 | 8.3773 | 18.6412 | 18.7877 | 0.0047 | 10.7391 | 40.4696 | 18.9646 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2