1
0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2024-12-24 09:00:27 +00:00
nanogpt-experiments/config/eval_gpt2_xl.py

9 lines
213 B
Python
Raw Normal View History

# evaluate the base gpt2
# n_layer=48, n_head=25, n_embd=1600
# 1558M parameters
batch_size = 8
eval_iters = 500 # use more iterations to get good estimate
eval_only = True
wandb_log = False
init_from = 'gpt2-xl'