mrm8488/t5-base-finetuned-common_gen

The T5 model was presented in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer . Google's T5 fine-tuned on CommonGen for Generative Commonsense Reasoning . The training script is a slightly modified version of this awesome one by Suraj Patil Patil . To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code. To see the training script, you can download the training code and train your own model and code to train your model with the same model and metrics for the same results shown in the paper. For example, a model trained on a pre-training task,