my_awesome_wnut_model_ / config.json
NastyaKorneeva's picture
Training in progress, epoch 1
a5768ed verified
raw
history blame contribute delete
995 Bytes
{
"_name_or_path": "cointegrated/rubert-tiny2",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"emb_size": 312,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 312,
"id2label": {
"0": "O",
"1": "B-Hard",
"2": "I-Hard",
"3": "B-Soft",
"4": "I-Soft",
"5": "B-Another",
"6": "I-Another"
},
"initializer_range": 0.02,
"intermediate_size": 600,
"label2id": {
"B-Another": 5,
"B-Hard": 1,
"B-Soft": 3,
"I-Another": 6,
"I-Hard": 2,
"I-Soft": 4,
"O": 0
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 2048,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 3,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.38.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 83828
}