Retrained with adaptive-classifier v0.0.17 (k parameter fix)

README.md

@@ -17,15 +17,15 @@ You can install it with `pip install adaptive-classifier`.
 
 - Base Model: answerdotai/ModernBERT-base
 - Number of Classes: 3
-- Total Examples: 246
+- Total Examples: 15
 - Embedding Dimension: 768
 
 ## Class Distribution
 
 ```
-low: 81 examples (32.9%)
-normal: 82 examples (33.3%)
-urgent: 83 examples (33.7%)
+low: 5 examples (33.3%)
+normal: 5 examples (33.3%)
+urgent: 5 examples (33.3%)
 ```
 
 ## Usage

config.json

@@ -42,5 +42,10 @@
     "urgent": 1
   },
   "model_name": "answerdotai/ModernBERT-base",
-  "train_steps": 8
+  "train_steps": 8,
+  "training_history": {
+    "low": 100,
+    "normal": 100,
+    "urgent": 100
+  }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c14fb2c51f328492dbf0a8faa81a2eea246f9312134975ac8d82681ba62b9c
+oid sha256:5c5509349b79132483ad9d2febc5e719033eff36acc35fe2fc0e76bfa38c7f07
 size 3558196