Pavarissy's picture
Training in progress, epoch 1
a272cb4
raw
history blame
1.4 kB
{
"_name_or_path": "airesearch/wangchanberta-base-att-spm-uncased",
"architectures": [
"CamembertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "NOUN",
"1": "PUNCT",
"2": "ADP",
"3": "NUM",
"4": "SYM",
"5": "SCONJ",
"6": "ADJ",
"7": "PART",
"8": "DET",
"9": "CCONJ",
"10": "PROPN",
"11": "PRON",
"12": "X",
"13": "_",
"14": "ADV",
"15": "INTJ",
"16": "VERB",
"17": "AUX"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"ADJ": 6,
"ADP": 2,
"ADV": 14,
"AUX": 17,
"CCONJ": 9,
"DET": 8,
"INTJ": 15,
"NOUN": 0,
"NUM": 3,
"PART": 7,
"PRON": 11,
"PROPN": 10,
"PUNCT": 1,
"SCONJ": 5,
"SYM": 4,
"VERB": 16,
"X": 12,
"_": 13
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "camembert",
"num_attention_head": 12,
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.34.1",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 25005
}