Ayham's picture
Update README.md
f38a4ff
|
raw
history blame
1.28 kB
metadata
tags:
  - generated_from_trainer
datasets:
  - cnn_dailymail
model-index:
  - name: roberta_gpt2_summarization_cnn_dailymail
    results: []

roberta_gpt2_summarization_cnn_dailymail

This model is a fine-tuned version of on the cnn_dailymail dataset.

Model description

This model uses RoBerta encoder and GPT2 decoder and fine-tuned on the summarization task. It got Rouge scores as follow:

Rouge1= 34.598 Rouge2= 16.66 RougeL= 26.259

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: 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: 2000
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.12.0.dev0
  • Pytorch 1.10.0+cu111
  • Datasets 1.16.1
  • Tokenizers 0.10.3