mirror of
https://github.com/osmarks/nanogpt-experiments.git
synced 2024-12-21 15:40:28 +00:00
9 lines
213 B
Python
9 lines
213 B
Python
# 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'
|