Update README.md

README.md

@@ -8,9 +8,6 @@ base_model:
 - Qwen/Qwen3-4B
 pipeline_tag: text-generation
 library_name: transformers
-metrics:
-- accuracy
-new_version: Arc-Intelligence/crm-01-4b
 ---
 
 ### **Model Card: Arc-Intelligence/crm-01-4b**
@@ -77,7 +74,7 @@ For full methodology and benchmark details, see our [blog post](../blog_post.md)
 
 ### **Training Data**
 
-The model was fine-tuned on the **B2B split** of the `CRMArena-Pro` dataset. This split covers **22 enterprise-grade tasks** spanning 4 business skill categories (Workflow, Policy, Text, Database) and 3 difficulty levels (Easy / Medium / Hard). The B2B training set contains **2,140** procedural workflow examples, all derived from a simulated Salesforce environment representative of real B2B organisations.
+The model was fine-tuned on the **B2B split** of the `CRMArena-Pro` dataset. This split covers **19 enterprise-grade tasks** spanning 4 business skill categories (Workflow, Policy, Text, Database) and 3 difficulty levels (Easy / Medium / Hard). The B2B training set contains **2,140** procedural workflow examples, all derived from a simulated Salesforce environment representative of real B2B organisations.
 
 ### **Training Procedure**