<!-- 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. -->
summarizing_literature
This model is a fine-tuned version of psin/my_awesome_billsum_model on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3867
- Rouge1: 0.105
- Rouge2: 0.015
- Rougel: 0.0858
- Rougelsum: 0.086
- 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: 72
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 19 | 3.5487 | 0.0994 | 0.0127 | 0.0816 | 0.0813 | 19.0 |
No log | 2.0 | 38 | 3.4905 | 0.1007 | 0.0137 | 0.0825 | 0.0823 | 19.0 |
No log | 3.0 | 57 | 3.4557 | 0.1006 | 0.0138 | 0.0832 | 0.0832 | 19.0 |
No log | 4.0 | 76 | 3.4327 | 0.0994 | 0.014 | 0.081 | 0.0809 | 19.0 |
No log | 5.0 | 95 | 3.4168 | 0.0992 | 0.0142 | 0.0817 | 0.0816 | 19.0 |
No log | 6.0 | 114 | 3.4049 | 0.0992 | 0.0127 | 0.0816 | 0.0818 | 19.0 |
No log | 7.0 | 133 | 3.3965 | 0.1024 | 0.0142 | 0.0838 | 0.0839 | 19.0 |
No log | 8.0 | 152 | 3.3909 | 0.1049 | 0.0156 | 0.086 | 0.0862 | 19.0 |
No log | 9.0 | 171 | 3.3878 | 0.1052 | 0.0156 | 0.0864 | 0.0865 | 19.0 |
No log | 10.0 | 190 | 3.3867 | 0.105 | 0.015 | 0.0858 | 0.086 | 19.0 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3