benchmarks/golden_configs/lm_wikitext2.py [12:24]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def get_model_config():
        return {
            "vocab_size": 10000,
            "ninp": 2048,  # embedding dimension
            "nhid": 2048,  # the dimension of the feedforward network model in nn.TransformerEncoder
            "nhead": 32,  # the number of heads in the multiheadattention models
            "dropout": 0,
            "initrange": 0.1,
            "scaler": GradScaler(),
            "clip_value": 0.05,
            "num_decoder_layers": 10,
            "seq_len": 32,
        }
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



benchmarks/golden_configs/lm_wikitext2.py [70:82]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def get_model_config():
        return {
            "vocab_size": 10000,
            "ninp": 2048,  # embedding dimension
            "nhid": 2048,  # the dimension of the feedforward network model in nn.TransformerEncoder
            "nhead": 32,  # the number of heads in the multiheadattention models
            "dropout": 0,
            "initrange": 0.1,
            "scaler": GradScaler(),
            "clip_value": 0.05,
            "num_decoder_layers": 10,
            "seq_len": 32,
        }
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -