t5-small-finetuned-scientific-articles
This model is a fine-tuned version of google-t5/t5-small on the scientific_papers dataset. It achieves the following results on the evaluation set:
- Loss: 3.2246
- Rouge1: 7.8805
- Rouge2: 2.622
- Rougel: 6.7327
- Rougelsum: 7.3172
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: 5.6e-05
- train_batch_size: 9
- eval_batch_size: 9
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 7.3084 | 1.0 | 56 | 5.4563 | 6.7162 | 2.0525 | 5.6729 | 6.2076 |
| 4.5048 | 2.0 | 112 | 3.8325 | 7.2382 | 2.4034 | 6.1187 | 6.674 |
| 3.7194 | 3.0 | 168 | 3.4523 | 7.7064 | 2.2556 | 6.4334 | 7.1049 |
| 3.5218 | 4.0 | 224 | 3.3173 | 8.1033 | 2.6122 | 6.8396 | 7.4375 |
| 3.4221 | 5.0 | 280 | 3.2246 | 7.8805 | 2.622 | 6.7327 | 7.3172 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1