lambdavi's picture
Training in progress, step 500
911584f
{
"_name_or_path": "studio-ousia/luke-base",
"architectures": [
"LukeForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bert_model_name": "roberta-base",
"bos_token_id": 0,
"classifier_dropout": null,
"entity_emb_size": 256,
"entity_vocab_size": 500000,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7,
"LABEL_8": 8
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "luke",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.35.0",
"type_vocab_size": 1,
"use_cache": true,
"use_entity_aware_attention": true,
"vocab_size": 50267
}