<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
my_xsum_billsum_model
This model is a fine-tuned version of ShubhamSP/my_awesome_billsum_model on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9629
- Rouge1: 0.247
- Rouge2: 0.0733
- Rougel: 0.1645
- Rougelsum: 0.164
- Gen Len: 67.05
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.2452 | 1.0 | 40 | 2.8062 | 0.243 | 0.0724 | 0.1745 | 0.1737 | 67.15 |
| 0.7262 | 2.0 | 80 | 2.9629 | 0.247 | 0.0733 | 0.1645 | 0.164 | 67.05 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
