sentiment-base-0 / config.json
apwic's picture
Training in progress, epoch 1
2ac48f5 verified
{
"_name_or_path": "indolem/indobert-base-uncased",
"adapters": {
"adapters": {},
"config_map": {},
"fusion_config_map": {},
"fusions": {}
},
"architectures": [
"BertAdapterModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"custom_heads": {},
"eos_token_ids": 0,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"0": 0,
"1": 1
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"prediction_heads": {
"default": {
"activation_function": "gelu",
"bias": true,
"embedding_size": 768,
"head_type": "masked_lm",
"label2id": null,
"layer_norm": true,
"layers": 2,
"shift_labels": false,
"vocab_size": 31923
},
"sentiment": {
"activation_function": "tanh",
"bias": true,
"dropout_prob": null,
"head_type": "classification",
"label2id": {
"0": 0,
"1": 1
},
"layers": 2,
"num_labels": 2,
"use_pooler": false
}
},
"torch_dtype": "float32",
"transformers_version": "4.39.3",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 31923
}