|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: bart-large-cnn-qmsum-meeting-summarization |
|
results: [] |
|
datasets: |
|
- yawnick/QMSum |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# bart-large-cnn-qmsum-meeting-summarization |
|
|
|
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 5.7578 |
|
- Rouge1: 37.9431 |
|
- Rouge2: 10.6366 |
|
- Rougel: 25.5782 |
|
- Rougelsum: 33.0209 |
|
- Gen Len: 72.7714 |
|
|
|
## 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: 3e-05 |
|
- 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 |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 500 |
|
- label_smoothing_factor: 0.1 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 2.0.0 |
|
- Tokenizers 0.11.6 |
|
|
