metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: bart-large-cnn-finetuned-laws_articles
results: []
bart-large-cnn-finetuned-laws_articles
This model is a fine-tuned version of facebook/bart-large-cnn on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1271
- Rouge1: 36.7269
- Rouge2: 16.9683
- Rougel: 27.0421
- Rougelsum: 28.4193
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
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 86 | 2.0321 | 36.6897 | 16.3485 | 27.3189 | 27.9101 |
| No log | 1.99 | 172 | 1.9454 | 38.9231 | 18.8033 | 29.5893 | 30.6478 |
| No log | 3.0 | 259 | 1.9194 | 39.8043 | 19.5213 | 29.9679 | 31.526 |
| No log | 3.99 | 345 | 1.9581 | 38.7543 | 18.0651 | 28.0544 | 29.5525 |
| No log | 4.99 | 431 | 2.0134 | 36.5099 | 17.177 | 27.2934 | 28.4522 |
| 1.5279 | 6.0 | 518 | 2.1271 | 36.7269 | 16.9683 | 27.0421 | 28.4193 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.7
- Tokenizers 0.14.1