f709e5d
1
2
3
4
5
6
7
8
9
# 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'