t5-small-finetuned-stock-news-2
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8004
- Rouge1: 44.167
- Rouge2: 36.0987
- Rougel: 42.3071
- Rougelsum: 42.7469
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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.9333 | 1.0 | 567 | 0.8685 | 43.2839 | 35.0416 | 41.431 | 41.724 |
| 0.8108 | 2.0 | 1134 | 0.8320 | 43.8366 | 35.6114 | 42.0042 | 42.3429 |
| 0.7762 | 3.0 | 1701 | 0.8183 | 43.6494 | 35.4373 | 41.755 | 42.1571 |
| 0.7487 | 4.0 | 2268 | 0.8084 | 43.8891 | 35.6917 | 41.9799 | 42.3663 |
| 0.7289 | 5.0 | 2835 | 0.8036 | 43.7749 | 35.5598 | 41.851 | 42.2422 |
| 0.7166 | 6.0 | 3402 | 0.8018 | 44.1163 | 36.0261 | 42.335 | 42.6929 |
| 0.7014 | 7.0 | 3969 | 0.8015 | 44.0648 | 35.8877 | 42.1801 | 42.6115 |
| 0.7119 | 8.0 | 4536 | 0.8004 | 44.167 | 36.0987 | 42.3071 | 42.7469 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1