khadija69's picture
Training in progress epoch 0
caa9f47
raw
history blame
1.17 kB
{
"_name_or_path": "khadija69/mdebertaV3_BIES_stem_1K_4",
"architectures": [
"DebertaV2ForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "B-Skill",
"1": "I-Skill",
"2": "E-Skill",
"3": "S-Skill",
"4": "B-O",
"5": "I-O",
"6": "E-O",
"7": "S-O"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-O": 4,
"B-Skill": 0,
"E-O": 6,
"E-Skill": 2,
"I-O": 5,
"I-Skill": 1,
"S-O": 7,
"S-Skill": 3
},
"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": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 768,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"relative_attention": true,
"share_att_key": true,
"transformers_version": "4.42.3",
"type_vocab_size": 0,
"vocab_size": 251000
}