SEBIS/code_trans_t5_large_transfer_learning_pretrain

The CodeTrans model is based on the t5-large 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 240,000 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-trained . It could be used to fine-tune other tasks in the development domain, such as fine-tuning tasks in software development . It was first released in this repository,