bhagasra-saurav's picture
Training in progress, step 500
beeb2d9
{
"_name_or_path": "bert-base-uncased",
"architectures": [
"BertForSequenceClassification"
],
"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": "a",
"1": "b",
"2": "c",
"3": "d",
"4": "e",
"5": "f",
"6": "g",
"7": "h",
"8": "i",
"9": "j",
"10": "k",
"11": "l",
"12": "m",
"13": "n",
"14": "o",
"15": "p",
"16": "q",
"17": "r",
"18": "s",
"19": "t",
"20": "u",
"21": "v",
"22": "w",
"23": "x",
"24": "y",
"25": "z"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"a": 0,
"b": 1,
"c": 2,
"d": 3,
"e": 4,
"f": 5,
"g": 6,
"h": 7,
"i": 8,
"j": 9,
"k": 10,
"l": 11,
"m": 12,
"n": 13,
"o": 14,
"p": 15,
"q": 16,
"r": 17,
"s": 18,
"t": 19,
"u": 20,
"v": 21,
"w": 22,
"x": 23,
"y": 24,
"z": 25
},
"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",
"problem_type": "multi_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}