MLQ-distilbart-bbc

This model is a fine-tuned version of sshleifer/distilbart-cnn-12-6 on the BBC News Summary dataset (https://www.kaggle.com/pariza/bbc-news-summary).

The model has been generated as part of the in-lab practice of Deep NLP course currently held at Politecnico di Torino.

Training parameters:

num_train_epochs=2
fp16=True
per_device_train_batch_size=1
warmup_steps=10
weight_decay=0.01
max_seq_length=100

Downloads last month: 27

Safetensors

Model size

306M params

Tensor type

F32

Inference Examples

Summarization

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for DeepNLP-22-23/MLQ-distilbart-bbc

Base model

sshleifer/distilbart-cnn-12-6

Finetuned

(26)

this model

Evaluation results

ROUGE-2 on bbc
test set self-reported

61.430

View on Papers With Code