t5-small-equadorKP
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0211
- Rouge1: 51.8765
- Rouge2: 37.0451
- Rougel: 51.7365
- Rougelsum: 51.7259
- Gen Len: 6.5792
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.171 | 1.0 | 6211 | 1.0792 | 50.847 | 37.011 | 50.7195 | 50.7905 | 6.4681 |
| 1.0127 | 2.0 | 12422 | 1.0760 | 51.2373 | 36.3082 | 51.0543 | 51.0786 | 6.5929 |
| 0.893 | 3.0 | 18633 | 1.0566 | 51.723 | 37.1819 | 51.5442 | 51.5984 | 6.7485 |
| 0.8944 | 4.0 | 24844 | 1.0580 | 51.1839 | 36.1186 | 50.969 | 50.9885 | 6.6299 |
| 0.8545 | 5.0 | 31055 | 1.0211 | 51.8765 | 37.0451 | 51.7365 | 51.7259 | 6.5792 |
| 0.8064 | 6.0 | 37266 | 1.0479 | 52.0241 | 37.6607 | 51.898 | 51.9317 | 6.4859 |
| 0.7433 | 7.0 | 43477 | 1.0473 | 51.9749 | 37.6617 | 51.8543 | 51.8594 | 6.4873 |
| 0.7496 | 8.0 | 49688 | 1.0570 | 52.2833 | 38.1133 | 52.1644 | 52.1668 | 6.5949 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2