NanoGPT_charToken / config /eval_gpt2_medium.py
RashiAgarwal's picture
Upload 6 files
4015e59
raw
history blame contribute delete
No virus
216 Bytes
# 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'