{
    "n_head": 6,
    "n_vocab": 50257,
    "embed_dropout": 0.1,
    "lr": 0.0006,
    "lr_decay": "cosine",
    "warmup_steps": 3000,
    "beta1": 0.9,
    "beta2": 0.95,
    "epsilon": 1e-8,
    "opt_name": "adam",
    "weight_decay": 0,
    "train_batch_size": 512,
    "attn_dropout": 0.1,
    "train_steps": 1000000,
    "lr_decay_end": 300000,
    "eval_steps": 30,
    "predict_steps": 0,
    "res_dropout": 0.1,
    "eval_batch_size": 128,
    "predict_batch_size": 8,
    "iterations": 2500,
    "n_embd": 768,
    "datasets": ["openwebtext2_new_inputs"],
    "model_path": "gs://neo-models/GPT2_SMALL",
    "n_ctx": 1024,
    "n_layer": 12,
    "scale_by_depth": true,
    "scale_by_in": false,
    "attention_types" :  [[["global"],12]],
    "activation_function": "gelu",
    "mesh_shape": "all:64",
    "layout": "batch:all",
    "recompute_grad": false,
    "gradient_clipping": 1.0
}