sibstrider's picture
Training in progress, epoch 1
0829b32 verified
raw
history blame
1.22 kB
{
"_name_or_path": "cointegrated/rubert-tiny2",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"emb_size": 312,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 312,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4",
"5": "LABEL_5",
"6": "LABEL_6",
"7": "LABEL_7",
"8": "LABEL_8",
"9": "LABEL_9",
"10": "LABEL_10"
},
"initializer_range": 0.02,
"intermediate_size": 600,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_10": 10,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4,
"LABEL_5": 5,
"LABEL_6": 6,
"LABEL_7": 7,
"LABEL_8": 8,
"LABEL_9": 9
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 2048,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 3,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 83828
}