|
--- |
|
license: mit |
|
datasets: |
|
- bhavyagiri/imdb-spoiler |
|
language: |
|
- en |
|
metrics: |
|
- accuracy |
|
- f1 |
|
pipeline_tag: text-classification |
|
tags: |
|
- text-classification |
|
- pytorch |
|
- roberta |
|
- imdb |
|
- spoilers |
|
widget: |
|
- text: Jack Ryan is so amazing |
|
--- |
|
|
|
|
|
The model trained from [roberta-base](https://huggingface.co/roberta-base) on the [imdb-spoiler](https://huggingface.co/datasets/bhavyagiri/imdb-spoiler) dataset for classification. |
|
|
|
[imdb-spoiler](https://huggingface.co/datasets/bhavyagiri/imdb-spoiler) is a subset of a [large-dataset](https://www.kaggle.com/datasets/rmisra/imdb-spoiler-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 0.773021 |
|
- Accuracy 0.783275 |
|
|
|
Labels: |
|
- 0 - Not Spoiler |
|
- 1 - Spoiler |
