my_awesome_billsum_model
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.4141
- Rouge1: 0.1902
- Rouge2: 0.0883
- Rougel: 0.1607
- Rougelsum: 0.1605
- 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 62 | 2.4766 | 0.1571 | 0.0575 | 0.1311 | 0.1309 | 19.0 |
No log | 2.0 | 124 | 2.4382 | 0.188 | 0.085 | 0.1577 | 0.1576 | 19.0 |
No log | 3.0 | 186 | 2.4194 | 0.1911 | 0.089 | 0.1612 | 0.161 | 19.0 |
No log | 4.0 | 248 | 2.4141 | 0.1902 | 0.0883 | 0.1607 | 0.1605 | 19.0 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 2