mirror of
https://github.com/osmarks/nanogpt-experiments.git
synced 2024-11-14 05:44:51 +00:00
9 lines
216 B
Python
9 lines
216 B
Python
# evaluate the base gpt2
|
|
# n_layer=24, n_head=16, n_embd=1024
|
|
# 350M parameters
|
|
batch_size = 8
|
|
eval_iters = 500 # use more iterations to get good estimate
|
|
eval_only = True
|
|
wandb_log = False
|
|
init_from = 'gpt2-medium'
|