metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: Super_legal_text_summarizer
results: []
Super_legal_text_summarizer
This model is a fine-tuned version of facebook/bart-large-cnn on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7796
- Rouge1: 0.3102
- Rouge2: 0.1753
- Rougel: 0.2022
- Rougelsum: 0.2037
- Gen Len: 142.0
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: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- 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 | 34 | 1.7714 | 0.3079 | 0.1651 | 0.1946 | 0.1965 | 142.0 |
| No log | 2.0 | 68 | 1.7531 | 0.3151 | 0.1752 | 0.207 | 0.2081 | 142.0 |
| No log | 3.0 | 102 | 1.7471 | 0.3041 | 0.1665 | 0.1963 | 0.198 | 142.0 |
| No log | 4.0 | 136 | 1.7520 | 0.3104 | 0.1727 | 0.2039 | 0.2053 | 142.0 |
| No log | 5.0 | 170 | 1.7547 | 0.3123 | 0.1747 | 0.2018 | 0.203 | 142.0 |
| No log | 6.0 | 204 | 1.7636 | 0.3079 | 0.169 | 0.1969 | 0.1984 | 142.0 |
| No log | 7.0 | 238 | 1.7691 | 0.3134 | 0.1783 | 0.2067 | 0.208 | 142.0 |
| No log | 8.0 | 272 | 1.7703 | 0.3082 | 0.1727 | 0.2023 | 0.204 | 142.0 |
| No log | 9.0 | 306 | 1.7746 | 0.3091 | 0.1753 | 0.2016 | 0.2034 | 142.0 |
| No log | 10.0 | 340 | 1.7796 | 0.3102 | 0.1753 | 0.2022 | 0.2037 | 142.0 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2