metadata
license: mit
base_model: facebook/bart-large-cnn
tags:
- generated_from_trainer
model-index:
- name: bart-cnn-dialogsum-finetuned
results: []
bart-cnn-dialogsum-finetuned
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: 0.5768
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: 1e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5847 | 1.0 | 78 | 0.6536 |
| 0.6067 | 2.0 | 156 | 0.6077 |
| 0.6014 | 3.0 | 234 | 0.5916 |
| 0.5525 | 4.0 | 312 | 0.5843 |
| 0.5465 | 5.0 | 390 | 0.5808 |
| 0.6124 | 6.0 | 468 | 0.5787 |
| 0.588 | 7.0 | 546 | 0.5774 |
| 0.5782 | 8.0 | 624 | 0.5776 |
| 0.5187 | 9.0 | 702 | 0.5771 |
| 0.4999 | 10.0 | 780 | 0.5768 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1