sohamtiwari3120's picture
Training in progress, epoch 1
c8bc135
raw
history blame
1.62 kB
{
"_name_or_path": "sohamtiwari3120/scideberta-cs-tdm-pretrained",
"architectures": [
"DebertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "O",
"1": "B-MethodName",
"2": "I-MethodName",
"3": "B-HyperparameterName",
"4": "I-HyperparameterName",
"5": "B-HyperparameterValue",
"6": "I-HyperparameterValue",
"7": "B-MetricName",
"8": "I-MetricName",
"9": "B-MetricValue",
"10": "I-MetricValue",
"11": "B-TaskName",
"12": "I-TaskName",
"13": "B-DatasetName",
"14": "I-DatasetName"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"B-DatasetName": 13,
"B-HyperparameterName": 3,
"B-HyperparameterValue": 5,
"B-MethodName": 1,
"B-MetricName": 7,
"B-MetricValue": 9,
"B-TaskName": 11,
"I-DatasetName": 14,
"I-HyperparameterName": 4,
"I-HyperparameterValue": 6,
"I-MethodName": 2,
"I-MetricName": 8,
"I-MetricValue": 10,
"I-TaskName": 12,
"O": 0
},
"layer_norm_eps": 1e-07,
"max_position_embeddings": 512,
"max_relative_positions": -1,
"model_type": "deberta",
"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": [
"c2p",
"p2c"
],
"position_biased_input": false,
"relative_attention": true,
"torch_dtype": "float32",
"transformers_version": "4.23.1",
"type_vocab_size": 0,
"vocab_size": 50265
}