Refine professional project description and metadata wording.

README.md

@@ -9,7 +9,7 @@ pinned: false
 
 # Math Conjecture Trainer Space
 
-Launch multi-stage DeepSeek-Math fine-tuning on Space GPU and push adapters to your model repo.
+An autonomous training operations console for DeepSeek-Math that runs multi-stage curriculum fine-tuning on Space GPU, executes post-training quality evaluation, and publishes only qualified adapters, checkpoints, and run reports to your Hugging Face model repository.
 
 This Space is the tactical operations console for `maths-conjuncture-solutions` and is wired to:
 

app.py

@@ -198,7 +198,7 @@ PROJECT_DESCRIPTION = """
 # Math Conjecture Trainer
 This console runs the full training operations lane for the `maths-conjuncture-solutions` project:
 
-Launch multi-stage DeepSeek-Math fine-tuning on Space GPU and push adapters to your model repo.
+An autonomous training operations console for DeepSeek-Math that runs multi-stage curriculum fine-tuning on Space GPU, executes post-training quality evaluation, and publishes only qualified adapters, checkpoints, and run reports to your Hugging Face model repository.
 
 1. Pull released parquet splits from `NorthernTribe-Research/math-conjecture-training-corpus`.
 2. Build runtime training configuration from `configs/deepseek_math_sota.yaml`.

configs/deepseek_math_sota.yaml

@@ -145,7 +145,7 @@ hub:
   repo_id: NorthernTribe-Research/math-conjecture-model
   private: false
   upload_stage_checkpoints: true
-  commit_message: Launch multi-stage DeepSeek-Math fine-tuning on Space GPU and push adapters to your model repo.
+  commit_message: Run autonomous multi-stage DeepSeek-Math training with post-eval quality gates and publish qualified adapters/checkpoints.
 
 credentials:
   path: huggingface-api-key.json