test-textsum-t5-1
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.4114
- Rouge1: 0.1898
- Rouge2: 0.0921
- Rougel: 0.1611
- Rougelsum: 0.161
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 62 | 2.4779 | 0.154 | 0.0601 | 0.1283 | 0.1281 | 19.0 |
| No log | 2.0 | 124 | 2.4391 | 0.1823 | 0.0871 | 0.1543 | 0.1542 | 19.0 |
| No log | 3.0 | 186 | 2.4182 | 0.1877 | 0.0902 | 0.1591 | 0.1591 | 19.0 |
| No log | 4.0 | 248 | 2.4114 | 0.1898 | 0.0921 | 0.1611 | 0.161 | 19.0 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3