234828b
1
2
3
4
5
6
7
8
9
# evaluate the base gpt2 # n_layer=12, n_head=12, n_embd=768 # 124M parameters batch_size = 8 eval_iters = 500 # use more iterations to get good estimate eval_only = True wandb_log = False init_from = 'gpt2'
