metadata

library_name: transformers
base_model:
  - facebook/bart-large-cnn
tags:
  - generated_from_trainer
model-index:
  - name: bart-text-simplification
    results: []
datasets:
  - facebook/asset
  - turk/simplification
language:
  - en
metrics:
  - sari

bart-text-simplification

Notes: the model is still under improvement

This model is a fine-tuned version of facebook/bart-large-cnn on ASSET and TurkCorpus dataset. It achieves the following results on the evaluation set:

eval_loss: 0.6558
eval_model_preparation_time: 0.0082
eval_sari: 59.0183
eval_runtime: 670.1131
eval_samples_per_second: 1.343
eval_steps_per_second: 1.343
step: 0

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: 1
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Tokenizers 0.19.1