Hugging Face's logo

samuellimabraz
/
bart-large-xsum-tweetsum

TensorBoard
Safetensors
bart
Generated from Trainer
Eval Results
Model card Files Metrics Community
bart-large-xsum-tweetsum / README.md
samuellimabraz's picture
samuellimabraz
End of training
48188b6 verified
preview code
|
raw
history blame contribute delete
No virus
1.77 kB
metadata
license: mit
base_model: facebook/bart-large-xsum
tags:
  - generated_from_trainer
datasets:
  - Andyrasika/TweetSumm-tuned
metrics:
  - rouge
model-index:
  - name: bart-large-xsum-tweetsum
    results:
      - task:
          name: Summarization
          type: summarization
        dataset:
          name: Andyrasika/TweetSumm-tuned
          type: Andyrasika/TweetSumm-tuned
        metrics:
          - name: Rouge1
            type: rouge
            value: 46.1359

Visualize in Weights & Biases

bart-large-xsum-tweetsum

This model is a fine-tuned version of facebook/bart-large-xsum on the Andyrasika/TweetSumm-tuned dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9921
  • Rouge1: 46.1359
  • Rouge2: 20.5196
  • Rougel: 38.6353
  • Rougelsum: 41.9642
  • Gen Len: 45.1

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Framework versions

  • Transformers 4.44.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1