Tahsin's picture
Training in progress, epoch 1
9d6927b
{
"_name_or_path": "bert-base-cased",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "\"",
"1": "''",
"10": "CC",
"11": "CD",
"12": "DT",
"13": "EX",
"14": "FW",
"15": "IN",
"16": "JJ",
"17": "JJR",
"18": "JJS",
"19": "LS",
"2": "#",
"20": "MD",
"21": "NN",
"22": "NNP",
"23": "NNPS",
"24": "NNS",
"25": "NN|SYM",
"26": "PDT",
"27": "POS",
"28": "PRP",
"29": "PRP$",
"3": "$",
"30": "RB",
"31": "RBR",
"32": "RBS",
"33": "RP",
"34": "SYM",
"35": "TO",
"36": "UH",
"37": "VB",
"38": "VBD",
"39": "VBG",
"4": "(",
"40": "VBN",
"41": "VBP",
"42": "VBZ",
"43": "WDT",
"44": "WP",
"45": "WP$",
"46": "WRB",
"5": ")",
"6": ",",
"7": ".",
"8": ":",
"9": "``"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"\"": "0",
"#": "2",
"$": "3",
"''": "1",
"(": "4",
")": "5",
",": "6",
".": "7",
":": "8",
"CC": "10",
"CD": "11",
"DT": "12",
"EX": "13",
"FW": "14",
"IN": "15",
"JJ": "16",
"JJR": "17",
"JJS": "18",
"LS": "19",
"MD": "20",
"NN": "21",
"NNP": "22",
"NNPS": "23",
"NNS": "24",
"NN|SYM": "25",
"PDT": "26",
"POS": "27",
"PRP": "28",
"PRP$": "29",
"RB": "30",
"RBR": "31",
"RBS": "32",
"RP": "33",
"SYM": "34",
"TO": "35",
"UH": "36",
"VB": "37",
"VBD": "38",
"VBG": "39",
"VBN": "40",
"VBP": "41",
"VBZ": "42",
"WDT": "43",
"WP": "44",
"WP$": "45",
"WRB": "46",
"``": "9"
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.15.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 28996
}