metadata
license: mit
datasets:
- bhavyagiri/imdb-spoiler
language:
- en
metrics:
- accuracy
- f1
pipeline_tag: text-classification
tags:
- text-classification
- pytorch
- roberta
- emotions
- multi-class-classification
- multi-label-classification
widget:
- text: Jack Ryan is so amazing
The model trained from roberta-base on the imdb-spoiler dataset for classification.
imdb-spoiler is a subset of a large-dataset for classifying whether a movie review is a spoiler or not.
The model was trained using AutoModelForSequenceClassification.from_pretrained for 3 epochs with a learning rate of 2e-5 and weight decay of 0.01.
Evaluation using the dataset validation split gives:
- F1 0.585
- Accuracy 0.474