Upload 10 files

config.json

@@ -0,0 +1,25 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "vocab_size": 119547
+}

evaluation_report.txt

@@ -0,0 +1,29 @@
+=== Name SMS Classifier - Evaluation Report ===
+
+Model: distilbert-base-multilingual-cased
+Training time: 2025-07-30 21:13:45
+
+=== Main Metrics ===
+Accuracy:  0.9977
+Precision: 0.9916
+Recall:    1.0000
+F1-Score:  0.9958
+ROC-AUC:   0.9998
+
+=== Confusion Matrix ===
+True\Pred   0(Not Name)  1(Name)
+0(Not Name)        625         2
+1(Name)              0       235
+
+=== 預測錯誤分析 ===
+總錯誤數: 2
+False Positive (誤判為姓名): 2
+False Negative (漏判姓名): 0
+
+--- False Positive 錯誤樣本 (前10個) ---
+1. 真實標籤: 0(非姓名), 預測標籤: 1(姓名), 信心度: 0.995
+   簡訊ID: 71773 簡訊內容: 高雄小華，您已報名「英語聽力測驗」並成功確認，測驗將於6月2日舉行，請攜帶有效身份證明文件。
+
+2. 真實標籤: 0(非姓名), 預測標籤: 1(姓名), 信心度: 0.995
+   簡訊ID: 111908 簡訊內容: 提醒您，系統顯示林誠支付平台會員編號FA5620帳務餘額為負NT$720，逾期未補繳將暫停交易與提款功能，請即刻處理以恢復帳戶正常。
+

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f386bb52592bf9d5f6ba0e5742f481c7e084eabe874c12514271602eaa6a15ae
+size 541317368

prediction_errors.csv

@@ -0,0 +1,3 @@
+sms_id,index,text,true_label,pred_label,error_type,confidence,prob_not_name,prob_name
+71773,143,高雄小華，您已報名「英語聽力測驗」並成功確認，測驗將於6月2日舉行，請攜帶有效身份證明文件。,0,1,False Positive,0.9946750402450562,0.005324934143573046,0.9946750402450562
+111908,241,提醒您，系統顯示林誠支付平台會員編號FA5620帳務餘額為負NT$720，逾期未補繳將暫停交易與提款功能，請即刻處理以恢復帳戶正常。,0,1,False Positive,0.994642972946167,0.005357014015316963,0.994642972946167

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_config.json

@@ -0,0 +1,15 @@
+{
+  "model_name": "distilbert-base-multilingual-cased",
+  "max_length": 512,
+  "batch_size": 16,
+  "learning_rate": 2e-05,
+  "num_epochs": 5,
+  "warmup_steps": 500,
+  "weight_decay": 0.01,
+  "random_seed": 42,
+  "device": "mps",
+  "use_wandb": true,
+  "wandb_project": "\"forensic-name-classifier\"",
+  "wandb_run_name": null,
+  "training_time": "2025-07-30T21:13:46.023856"
+}