gpt_2_124M / train.py

Commit History

Initial commit of GPT-2 46M SwiGLU Dense baseline model architecture and configs
8d74481
verified

Soham Jain commited on

Initial commit of GPT-2 46M SwiGLU Dense baseline model architecture and configs
1030cb2
verified

Soham Jain commited on

Initial commit of GPT-2 46M SwiGLU Dense baseline model architecture and configs
7679431
verified

Soham Jain commited on

Initial commit of 124M GPT-2 baseline files with step-by-step logging and 50-step val interval
ea8f100
verified

Soham Jain commited on