The goal is to train the GPT2 model to extrapolate on a movie review and generate negative sentiment.
There is a separate training done to generate positive movie reviews. The eventual goal would be to interpolate the weight spaces of the 'positively fintuned' and 'negatively finetuned' models as per the rewarded-soups paper and test if it results in (qualitatively) neutral reviews.
Model Params
Here are the traning parameters
base_model ='lvwerra/gpt2-imdb'
dataset = stanfordnlp/imdb
batch_size = 16
learning_rate = 1.41e-5
output_max_length = 16
output_min_length = 4
Not sure how long it took, but less than a couple hours on a single A6000 GPU
