Add eval artifacts (test)

eval/classification_report_test.csv

@@ -0,0 +1,7 @@
+,precision,recall,f1-score,support
+LABEL_0,0.9630872483221476,0.9566666666666667,0.959866220735786,300.0
+LABEL_1,0.9341692789968652,0.9900332225913622,0.9612903225806452,301.0
+LABEL_2,0.9859649122807017,0.9335548172757475,0.9590443686006825,301.0
+accuracy,0.9600886917960089,0.9600886917960089,0.9600886917960089,0.9600886917960089
+macro avg,0.9610738131999049,0.9600849021779254,0.9600669706390379,902.0
+weighted avg,0.9610715810101905,0.9600886917960089,0.9600671931999062,902.0

eval/confusion_matrix_test.csv

@@ -0,0 +1,4 @@
+,P_LABEL_0,P_LABEL_1,P_LABEL_2
+T_LABEL_0,287,10,3
+T_LABEL_1,2,298,1
+T_LABEL_2,9,11,281

eval/metrics_test.json

@@ -0,0 +1,12 @@
+{
+  "split": "test",
+  "timestamp": "2025-09-05 18:54:03",
+  "num_examples": 902,
+  "accuracy": 0.9600886917960089,
+  "precision_weighted": 0.9610715810101905,
+  "recall_weighted": 0.9600886917960089,
+  "f1_weighted": 0.9600671931999062,
+  "precision_macro": 0.9610738131999049,
+  "recall_macro": 0.9600849021779254,
+  "f1_macro": 0.9600669706390379
+}