joshuaphua's picture
Training in progress, epoch 1
8ec2bc2 verified
raw
history blame
1.15 kB
{
"_name_or_path": "dslim/distilbert-NER",
"activation": "gelu",
"architectures": [
"DistilBertForTokenClassification"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"id2label": {
"0": "O",
"1": "B-PER",
"2": "I-PER",
"3": "B-ORG",
"4": "I-ORG",
"5": "B-LOC",
"6": "I-LOC",
"7": "B-MISC",
"8": "I-MISC",
"9": "B-JOB",
"10": "I-JOB",
"11": "B-MAJ",
"12": "I-MAJ",
"13": "B-SKILL",
"14": "I-SKILL"
},
"initializer_range": 0.02,
"label2id": {
"B-JOB": 9,
"B-LOC": 5,
"B-MAJ": 11,
"B-MISC": 7,
"B-ORG": 3,
"B-PER": 1,
"B-SKILL": 13,
"I-JOB": 10,
"I-LOC": 6,
"I-MAJ": 12,
"I-MISC": 8,
"I-ORG": 4,
"I-PER": 2,
"I-SKILL": 14,
"O": 0
},
"max_position_embeddings": 512,
"model_type": "distilbert",
"n_heads": 12,
"n_layers": 6,
"output_past": true,
"pad_token_id": 0,
"qa_dropout": 0.1,
"seq_classif_dropout": 0.2,
"sinusoidal_pos_embds": false,
"tie_weights_": true,
"torch_dtype": "float32",
"transformers_version": "4.33.2",
"vocab_size": 28996
}