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: 3.4361
- Rouge1: 0.1396
- Rouge2: 0.0447
- Rougel: 0.1173
- Rougelsum: 0.1174
- 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: 128
- eval_batch_size: 128
- 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 | 8 | 4.1677 | 0.1431 | 0.0488 | 0.121 | 0.1211 | 19.0 |
No log | 2.0 | 16 | 3.7195 | 0.1417 | 0.0471 | 0.1197 | 0.1198 | 19.0 |
No log | 3.0 | 24 | 3.5005 | 0.1408 | 0.0456 | 0.1185 | 0.1185 | 19.0 |
No log | 4.0 | 32 | 3.4361 | 0.1396 | 0.0447 | 0.1173 | 0.1174 | 19.0 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 2