TimKoornstra / FinTwitBERT

FinTwitBERT: Specialized BERT Model for Financial Twitter Analysis. Trained on vast financial tweets, it's ideal for sentiment analysis, trend prediction, and financial NLP tasks.
MIT License
5 stars 1 forks source link

Add a config file for hyperparameters and other #8

Closed StephanAkkerman closed 8 months ago

StephanAkkerman commented 9 months ago

In the config file we should add parameters we often change and the ability to toggle kfold

TimKoornstra commented 9 months ago

Or we use argparser and write our arg settings to a config.json that we store with the model

StephanAkkerman commented 8 months ago

Also include extra parameters like gradual_unfreeze