deprel_cs / config.json
izaitova's picture
Training in progress, step 500
1dfbe0d verified
raw
history blame
2.68 kB
{
"_name_or_path": "google/mt5-large",
"architectures": [
"MT5ForTokenClassification"
],
"classifier_dropout": 0.0,
"d_ff": 2816,
"d_kv": 64,
"d_model": 1024,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8",
"9": "LABEL_9",
"10": "LABEL_10",
"11": "LABEL_11",
"12": "LABEL_12",
"13": "LABEL_13",
"14": "LABEL_14",
"15": "LABEL_15",
"16": "LABEL_16",
"17": "LABEL_17",
"18": "LABEL_18",
"19": "LABEL_19",
"20": "LABEL_20",
"21": "LABEL_21",
"22": "LABEL_22",
"23": "LABEL_23",
"24": "LABEL_24",
"25": "LABEL_25",
"26": "LABEL_26",
"27": "LABEL_27",
"28": "LABEL_28",
"29": "LABEL_29",
"30": "LABEL_30",
"31": "LABEL_31",
"32": "LABEL_32",
"33": "LABEL_33",
"34": "LABEL_34",
"35": "LABEL_35",
"36": "LABEL_36",
"37": "LABEL_37",
"38": "LABEL_38",
"39": "LABEL_39",
"40": "LABEL_40",
"41": "LABEL_41",
"42": "LABEL_42",
"43": "LABEL_43"
},
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_10": 10,
"LABEL_11": 11,
"LABEL_12": 12,
"LABEL_13": 13,
"LABEL_14": 14,
"LABEL_15": 15,
"LABEL_16": 16,
"LABEL_17": 17,
"LABEL_18": 18,
"LABEL_19": 19,
"LABEL_2": 2,
"LABEL_20": 20,
"LABEL_21": 21,
"LABEL_22": 22,
"LABEL_23": 23,
"LABEL_24": 24,
"LABEL_25": 25,
"LABEL_26": 26,
"LABEL_27": 27,
"LABEL_28": 28,
"LABEL_29": 29,
"LABEL_3": 3,
"LABEL_30": 30,
"LABEL_31": 31,
"LABEL_32": 32,
"LABEL_33": 33,
"LABEL_34": 34,
"LABEL_35": 35,
"LABEL_36": 36,
"LABEL_37": 37,
"LABEL_38": 38,
"LABEL_39": 39,
"LABEL_4": 4,
"LABEL_40": 40,
"LABEL_41": 41,
"LABEL_42": 42,
"LABEL_43": 43,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7,
"LABEL_8": 8,
"LABEL_9": 9
},
"layer_norm_epsilon": 1e-06,
"model_type": "mt5",
"num_decoder_layers": 24,
"num_heads": 16,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"tokenizer_class": "T5Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.39.3",
"use_cache": true,
"vocab_size": 250112
}