SEBIS/code_trans_t5_base_transfer_learning_pretrain

The CodeTrans model is based on the t5-base model . It used transfer-learning pre-training on 7 unsupervised datasets in the software development domain . The model was trained on a single TPU Pod V3-8 for half million steps in total, using sequence length 512 (batch size 4096) It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture . The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-trainings . It could be used to fine-tune other tasks in the development domain, such as fine-tuning software development tasks . It was first released in this repository .,