{ | |
"architectures": [ | |
"GPT2LMHeadModel" | |
], | |
"auto_map": { | |
"AutoConfig": "GPT2Tokenizer", | |
"AutoModel": "GPT2LMHeadModel" | |
}, | |
"batch_size": 12, | |
"block_size": 100, | |
"device": "cpu", | |
"eval_interval": 250, | |
"hidden_dropout_prob": 0.0, | |
"n_embd": 300, | |
"n_head": 6, | |
"n_layer": 6, | |
"learning_rate": 0.001, | |
"max_iters": 6000, | |
"torch_dtype": "float16", | |
"transformers_version": "4.33.2", | |
"vocab_size": 1000 | |
} | |