t5-small-finetuned-stock-news
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4747
- Rouge1: 46.0644
- Rouge2: 39.4287
- Rougel: 44.2891
- Rougelsum: 44.7063
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: 2.5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.7374 | 1.0 | 536 | 0.5167 | 45.1623 | 38.2243 | 43.3029 | 43.7977 |
| 0.6017 | 2.0 | 1072 | 0.4906 | 45.8833 | 39.0776 | 44.0058 | 44.4512 |
| 0.5731 | 3.0 | 1608 | 0.4768 | 45.8351 | 39.1234 | 43.9974 | 44.4038 |
| 0.5594 | 4.0 | 2144 | 0.4747 | 46.0644 | 39.4287 | 44.2891 | 44.7063 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1