Upload 7 files

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "beomi/KcBERT-v2023",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

requirements.txt

@@ -0,0 +1,7 @@
+pandas
+torch
+transformers
+scikit-learn
+datasets
+numpy
+streamlit

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

모델학습평가결과.txt

@@ -0,0 +1,68 @@
+ethics/텍스트윤리검증데이터/aihub_텍스트윤리검증데이터_중복제거_061424.csv
+
+[340225, 42528, 42529]
+
+id2label=
+{'IMMORAL_NONE': 0,
+ 'CRIME': 1,
+ 'SEXUAL': 2,
+ 'HATE': 3,
+ 'DISCRIMINATION': 4,
+ 'CENSURE': 5,
+ 'ABUSE': 6,
+ 'VIOLENCE': 7}
+
+** 'eval_mean_accuracy': 0.8997096099132357
+Test Results: {'eval_loss': 0.2841951251029968, 'eval_mean_accuracy': 0.8997096099132357, 'eval_f1': 0.644721372735319, 'eval_confusion_matrix': [[[20635, 3291], [4694, 13909]], [[41636, 128], [677, 88]], [[39671, 594], [1215, 1049]], [[34075, 1806], [4632, 2016]], [[37842, 823], [3098, 766]], [[18147, 4960], [5105, 14317]], [[40260, 394], [1274, 601]], [[40177, 471], [960, 921]]], 'eval_accuracy_0': 0.8122457617155353, 'eval_accuracy_1': 0.9810717392837829, 'eval_accuracy_2': 0.9574643184650474, 'eval_accuracy_3': 0.8486209410049613, 'eval_accuracy_4': 0.9078040866232453, 'eval_accuracy_5': 0.763337957628912, 'eval_accuracy_6': 0.960779703261304, 'eval_accuracy_7': 0.9663523713230971, 'eval_runtime': 75.362, 'eval_samples_per_second': 564.33, 'eval_steps_per_second': 35.283, 'epoch': 10.0}
+
+Confusion Matrix for Label IMMORAL_NONE:
+[[20635  3291]
+ [ 4694 13909]]
+Confusion Matrix for Label CRIME:
+[[41636   128]
+ [  677    88]]
+Confusion Matrix for Label SEXUAL:
+[[39671   594]
+ [ 1215  1049]]
+Confusion Matrix for Label HATE:
+[[34075  1806]
+ [ 4632  2016]]
+Confusion Matrix for Label DISCRIMINATION:
+[[37842   823]
+ [ 3098   766]]
+Confusion Matrix for Label CENSURE:
+[[18147  4960]
+ [ 5105 14317]]
+Confusion Matrix for Label ABUSE:
+[[40260   394]
+ [ 1274   601]]
+Confusion Matrix for Label VIOLENCE:
+[[40177   471]
+ [  960   921]]
+
+
+각 레이블별 정확도와 F1 점수
+IMMORAL_NONE:
+Accuracy: 0.7582
+F1 Score: 0.7771
+CRIME:
+Accuracy: 0.9853
+F1 Score: 0.1807
+SEXUAL:
+Accuracy: 0.9575
+F1 Score: 0.5375
+HATE:
+Accuracy: 0.8760
+F1 Score: 0.3861
+DISCRIMINATION:
+Accuracy: 0.9164
+F1 Score: 0.2805
+CENSURE:
+Accuracy: 0.7706
+F1 Score: 0.7397
+ABUSE:
+Accuracy: 0.9551
+F1 Score: 0.4176
+VIOLENCE:
+Accuracy: 0.9748
+F1 Score: 0.5619