t5-small-finetuned-xsum-custom-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: 2.3786
- Rouge1: 31.4362
- Rouge2: 9.6838
- Rougel: 25.2999
- Rougelsum: 25.2866
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: 4e-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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.8203 | 1.0 | 5014 | 2.4866 | 29.4445 | 8.3337 | 23.5606 | 23.5476 |
| 2.6588 | 2.0 | 10028 | 2.4326 | 30.325 | 8.9839 | 24.2942 | 24.2757 |
| 2.5898 | 3.0 | 15042 | 2.4066 | 30.6845 | 9.2984 | 24.7842 | 24.7798 |
| 2.5414 | 4.0 | 20056 | 2.3909 | 31.2002 | 9.4684 | 25.0031 | 24.996 |
| 2.5094 | 5.0 | 25070 | 2.3796 | 31.3796 | 9.6549 | 25.2979 | 25.2858 |
| 2.4899 | 6.0 | 30084 | 2.3786 | 31.4362 | 9.6838 | 25.2999 | 25.2866 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1