Model/COSMIC/feature_extraction/comet/config/conceptnet/config_0.json

{
    "gpu_mode": "T",
    "gpu_index": 0,
    "gpu_indices": [
        0,
        1
    ],
    "multigpu": "F",
    "topk_size": 10,
    "beam_size": 1,
    "gen_seqlength": 40,
    "eval_sampler": "greedy",
    "num_sequences": 1,
    "generate_sequences": "full",
    "evaluate_sequences": "full",
    "random_seed": 123,
    "optimizer": "adam",
    "batch_size": 64,
    "learning_rate": 1e-05,
    "clip": 1,
    "loss": "nll",
    "weight_decay": 0,
    "adam": {
        "b2": 0.999,
        "b1": 0.9,
        "e": 1e-08
    },
    "model": "transformer",
    "pretrain": "gpt",
    "hidden_dim": 768,
    "num_layers": 12,
    "num_heads": 12,
    "embedding_dropout": 0.1,
    "attention_dropout": 0.1,
    "residual_dropout": 0.1,
    "output_dropout": 0.1,
    "activation": "gelu",
    "init": "pt",
    "trainer": "iteration",
    "iterations": 100000,
    "cycle": 500,
    "save_strategy": "best",
    "epochs": 20,
    "toy": "F",
    "do_gen": "T",
    "save": "T",
    "test_save": "F",
    "dataset": "conceptnet",
    "exp": "generation",
    "encoder_path": "model/encoder_bpe_40000.json",
    "bpe_path": "model/vocab_40000.bpe",
    "learning_rate_schedule": "warmup_linear",
    "learning_rate_warmup": 0.002,
    "l2": 0.01,
    "vector_l2": "T",
    "relation_format": "language",
    "training_set_size": 100,
    "development_set_versions_to_use": "12",
    "max_event_1_size": 10,
    "max_event_2_size": 15
}