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

README.md

@@ -17,16 +17,16 @@ You can install it with `pip install adaptive-classifier`.
 
 - Base Model: answerdotai/ModernBERT-base
 - Number of Classes: 4
-- Total Examples: 329
+- Total Examples: 20
 - Embedding Dimension: 768
 
 ## Class Distribution
 
 ```
-english: 82 examples (24.9%)
-french: 83 examples (25.2%)
-other: 82 examples (24.9%)
-spanish: 82 examples (24.9%)
+english: 5 examples (25.0%)
+french: 5 examples (25.0%)
+other: 5 examples (25.0%)
+spanish: 5 examples (25.0%)
 ```
 
 ## Usage

config.json

@@ -44,5 +44,11 @@
     "spanish": 3
   },
   "model_name": "answerdotai/ModernBERT-base",
-  "train_steps": 11
+  "train_steps": 11,
+  "training_history": {
+    "english": 100,
+    "french": 100,
+    "other": 100,
+    "spanish": 100
+  }
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b55b38f1092446591f208106b35ef2c21c5c20bbec5959a9941e1aa78509e7
+oid sha256:2dcc15fa9cea1dc04c4140eaa0ca5db22472ef53dc6ca5dad13b79a615de9b41
 size 3562896