wip deepseek r1

procedures/self_improvement/reasoning.md

@@ -309,8 +309,9 @@ This preserves the temporal relationships between entries while anchoring them t
 
 ## Training Configuration
 
-SIA takes a modular approach to model training by having separate specialized tools for each provider like train_mistral.py, train_openai.py, etc.
+SIA takes a modular approach to model training by having separate specialized tools for each provider like train_mistral, train_deepseek, etc.
 Each tool shares similar core functionality while handling provider-specific requirements.
+The default training tool and parameters are called from the `/root/sia/tools/train/train.sh` script.
 
 While the training process is conceptually similar across providers, each has unique requirements for data formatting, API interactions, and job management.
 By creating dedicated tools, we can properly encapsulate these differences without complicating the core training logic.
@@ -341,29 +342,6 @@ This separation of concerns makes it easier to:
 - Handle provider-specific error cases and requirements appropriately
 - Update individual providers' implementations as their APIs evolve
 
-### Example
-
-Config file:
-
-```yaml
-model:
-  system_prompt_path: "system_prompt.md"
-  action_schema: "action_schema.xsd"
-params:
-  learning_rate: 1e-5
-  epochs: 3
-data:
-  - "training/clean_start/"
-  - "training/delete_indicated_entries/"
-  - "training/list_entries_to_delete/"
-```
-
-Training command:
-
-```bash
-python train_mistral.py --model mistral-large-latest
-```
-
 ## Repository Structure
 
 All components that define SIA's behavior are version controlled in a single repository, providing a clear and reproducible state for any point in time.