summarizer_model
This model is a fine-tuned version of t5-small on the scientific_papers dataset. It achieves the following results on the evaluation set:
- Loss: 2.0439
- Rouge1: 0.1421
- Rouge2: 0.0605
- Rougel: 0.1217
- Rougelsum: 0.1217
- Gen Len: 19.0
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.3508 | 1.0 | 3748 | 2.1086 | 0.1416 | 0.0607 | 0.1216 | 0.1216 | 19.0 |
| 2.2857 | 2.0 | 7496 | 2.0675 | 0.1421 | 0.0603 | 0.1216 | 0.1216 | 19.0 |
| 2.2583 | 3.0 | 11244 | 2.0477 | 0.1423 | 0.0605 | 0.1217 | 0.1217 | 19.0 |
| 2.2437 | 4.0 | 14992 | 2.0439 | 0.1421 | 0.0605 | 0.1217 | 0.1217 | 19.0 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2