f4e648b
1
2
3
4
5
6
7
8
9
10
11
12
{ "batch_size": 32, "block_size": 256, "max_iters": 3000, "eval_interval": 300, "learning_rate": 3e-5, "eval_iters": 50, "n_embd": 1024, "n_head": 12, "n_layer": 18, "dropout": 0.3 }
