metadata

license: mit
base_model: facebook/mbart-large-50
tags:
  - summarization
  - generated_from_trainer
datasets:
  - mlsum
model-index:
  - name: mbart-large-50-finetuned-mBART50
    results: []

mbart-large-50-finetuned-mBART50

This model is a fine-tuned version of facebook/mbart-large-50 on the mlsum dataset. It achieves the following results on the evaluation set:

eval_loss: 4.3657
eval_rouge1: 31.5055
eval_rouge2: 23.392
eval_rougeL: 28.9957
eval_rougeLsum: 30.2596
eval_runtime: 9404.8054
eval_samples_per_second: 0.286
eval_steps_per_second: 0.036
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: 5.6e-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
num_epochs: 4

Framework versions

Transformers 4.41.2
Pytorch 2.3.0
Datasets 2.19.2
Tokenizers 0.19.1