my_test_billsum_model
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5228
- Rouge1: 0.141
- Rouge2: 0.0489
- Rougel: 0.1157
- Rougelsum: 0.1158
- 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 | 2.8147 | 0.1265 | 0.0394 | 0.1087 | 0.1087 | 19.0 |
No log | 2.0 | 124 | 2.6051 | 0.1355 | 0.0443 | 0.1125 | 0.1125 | 19.0 |
No log | 3.0 | 186 | 2.5396 | 0.1387 | 0.0478 | 0.1145 | 0.1145 | 19.0 |
No log | 4.0 | 248 | 2.5228 | 0.141 | 0.0489 | 0.1157 | 0.1158 | 19.0 |
Framework versions
- Transformers 4.41.2
- Pytorch 1.13.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2