metadata

license: apache-2.0
base_model: facebook/bart-large
tags:
  - generated_from_trainer
model-index:
  - name: bart-large
    results: []
datasets:
  - EdinburghNLP/xsum

bart-large

This model is a fine-tuned version for single sentence summarization of facebook/bart-large on the EdinburghNLP/XSum dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

Trained on 9k rows of data.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2