thusken's picture
Training in progress, epoch 1
f4405d8
raw
history blame
1.26 kB
{
"_name_or_path": "NbAiLab/nb-bert-base",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "need_divert",
"1": "need_educate",
"2": "need_inspire",
"3": "need_perspective",
"4": "need_trend",
"5": "need_update"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"need_divert": "0",
"need_educate": "1",
"need_inspire": "2",
"need_perspective": "3",
"need_trend": "4",
"need_update": "5"
},
"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": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.17.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}