bobbyw's picture
Training in progress, step 500
f554b8e verified
{
"_name_or_path": "bobbyw/deberta-v3-large_v3_mentioned_common_entities",
"architectures": [
"DebertaV2ForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "attendee",
"1": "probability",
"2": "trip",
"3": "location",
"4": "date",
"5": "accommodation",
"6": "cost",
"7": "unstructured_information",
"8": "itinerary",
"9": "flight",
"10": "travel",
"11": "arrival_city",
"12": "departure_city",
"13": "preference",
"14": "activity",
"15": "link"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"accommodation": 5,
"activity": 14,
"arrival_city": 11,
"attendee": 0,
"cost": 6,
"date": 4,
"departure_city": 12,
"flight": 9,
"itinerary": 8,
"link": 15,
"location": 3,
"preference": 13,
"probability": 1,
"travel": 10,
"trip": 2,
"unstructured_information": 7
},
"layer_norm_eps": 1e-07,
"max_position_embeddings": 512,
"max_relative_positions": -1,
"model_type": "deberta-v2",
"norm_rel_ebd": "layer_norm",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 1024,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"problem_type": "multi_label_classification",
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.41.2",
"type_vocab_size": 0,
"vocab_size": 128041
}