aliosm/ComVE-distilgpt2

The model is able to generate a reason why a given natural language statement is against commonsense . You can use the raw model for text generation to generate reasons why natural language statements are against common sense . The model achieved 13.7582/13.8026 BLEU scores on SemEval2020 Task4: Commonsense Validation and Explanation development and testing dataset. The model was trained on Nvidia Tesla P100 GPU from Google Colab platform with 5e-5 learning rate, 15 epochs, 128 maximum sequence length and 64 batch size. It was finetuned using a causal language modeling (CLM) objective. It is based on ComVE dataset which contains 10K,