aadhistii's picture
Training in progress, epoch 1
1e4bdf5 verified
raw
history blame
1.51 kB
{
"_name_or_path": "bert-base-multilingual-cased",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "SDG1",
"1": "SDG2",
"2": "SDG3",
"3": "SDG4",
"4": "SDG5",
"5": "SDG6",
"6": "SDG7",
"7": "SDG8",
"8": "SDG9",
"9": "SDG10",
"10": "SDG11",
"11": "SDG12",
"12": "SDG13",
"13": "SDG14",
"14": "SDG15",
"15": "SDG16",
"16": "SDG17"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"SDG1": 0,
"SDG10": 9,
"SDG11": 10,
"SDG12": 11,
"SDG13": 12,
"SDG14": 13,
"SDG15": 14,
"SDG16": 15,
"SDG17": 16,
"SDG2": 1,
"SDG3": 2,
"SDG4": 3,
"SDG5": 4,
"SDG6": 5,
"SDG7": 6,
"SDG8": 7,
"SDG9": 8
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"problem_type": "multi_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.44.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}