dipudl's picture
Training in progress, step 500
7ece1e4
{
"_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 384,
"id2label": {
"0": "cs",
"1": "math",
"2": "physics",
"3": "eess",
"4": "cond-mat",
"5": "q-bio",
"6": "stat",
"7": "hep-ph",
"8": "math-ph",
"9": "hep-th",
"10": "astro-ph",
"11": "gr-qc",
"12": "nlin",
"13": "quant-ph",
"14": "nucl-th",
"15": "q-fin",
"16": "nucl-ex",
"17": "hep-ex",
"18": "econ",
"19": "hep-lat"
},
"initializer_range": 0.02,
"intermediate_size": 1536,
"label2id": {
"astro-ph": 10,
"cond-mat": 4,
"cs": 0,
"econ": 18,
"eess": 3,
"gr-qc": 11,
"hep-ex": 17,
"hep-lat": 19,
"hep-ph": 7,
"hep-th": 9,
"math": 1,
"math-ph": 8,
"nlin": 12,
"nucl-ex": 16,
"nucl-th": 14,
"physics": 2,
"q-bio": 5,
"q-fin": 15,
"quant-ph": 13,
"stat": 6
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.20.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}