harkase's picture
End of training
c68aa70 verified
{
"architectures": [
"ElectraForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"embedding_size": 768,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "enfj",
"1": "enfp",
"2": "entj",
"3": "entp",
"4": "esfj",
"5": "esfp",
"6": "estj",
"7": "estp",
"8": "infj",
"9": "infp",
"10": "intj",
"11": "intp",
"12": "isfj",
"13": "isfp",
"14": "istj",
"15": "istp"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"enfj": 0,
"enfp": 1,
"entj": 2,
"entp": 3,
"esfj": 4,
"esfp": 5,
"estj": 6,
"estp": 7,
"infj": 8,
"infp": 9,
"intj": 10,
"intp": 11,
"isfj": 12,
"isfp": 13,
"istj": 14,
"istp": 15
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "electra",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"summary_activation": "gelu",
"summary_last_dropout": 0.1,
"summary_type": "first",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.55.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 35000
}