my_awesome_billsum_model
This model is a LSTM with a Attention Layer trained on the billsum dataset a subset of Samsum Corpus. It achieves the following results on the evaluation set:
- Loss: 2.5080
- Rouge1: 0.1397
- Rouge2: 0.0498
- Rougel: 0.1153
- Rougelsum: 0.1155
- 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 | 2.8004 | 0.1251 | 0.0337 | 0.1032 | 0.1031 | 19.0 |
| No log | 2.0 | 124 | 2.5885 | 0.1357 | 0.0436 | 0.1114 | 0.1114 | 19.0 |
| No log | 3.0 | 186 | 2.5255 | 0.1372 | 0.0454 | 0.1123 | 0.1125 | 19.0 |
| No log | 4.0 | 248 | 2.5080 | 0.1397 | 0.0498 | 0.1153 | 0.1155 | 19.0 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Downloads last month
- 2