dhlanm's picture
Training in progress, epoch 1
6b9e63e
{
"_name_or_path": "distilbert-base-uncased",
"activation": "gelu",
"architectures": [
"DistilBertForTokenClassification"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"id2label": {
"0": "O",
"1": "B-Hedging",
"10": "I-Possibly-Filler",
"11": "B-Possibly-Sensitive",
"12": "I-Possibly-Sensitive",
"13": "B-Profane",
"14": "I-Profane",
"2": "I-Hedging",
"3": "B-Filler",
"4": "I-Filler",
"5": "B-Sensitive",
"6": "I-Sensitive",
"7": "B-Possibly-Hedging",
"8": "I-Possibly-Hedging",
"9": "B-Possibly-Filler"
},
"initializer_range": 0.02,
"label2id": {
"B-Filler": "3",
"B-Hedging": "1",
"B-Possibly-Filler": "9",
"B-Possibly-Hedging": "7",
"B-Possibly-Sensitive": "11",
"B-Profane": "13",
"B-Sensitive": "5",
"I-Filler": "4",
"I-Hedging": "2",
"I-Possibly-Filler": "10",
"I-Possibly-Hedging": "8",
"I-Possibly-Sensitive": "12",
"I-Profane": "14",
"I-Sensitive": "6",
"O": "0"
},
"max_position_embeddings": 512,
"model_type": "distilbert",
"n_heads": 12,
"n_layers": 6,
"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": "4.18.0",
"vocab_size": 30522
}