This model is a fine-tuned version of
facebook/bart-base on the multi_news dataset.
It achieves the following results on the evaluation set:
The inteded use of this model is text summarization.
The model requires additional training in order to perform better in the task of summarization.
The training data were 10000 samples from the multi-news training dataset
and the evaluation data were 500 samples from the multi-news evaluation dataset
For the training procedure the Seq2SeqTrainer class was used from the transformers library.
The Hyperparameters were passed to the Seq2SeqTrainingArguments class from the transformers library.
