📚 KB / Corlera AI Training Lab / Experiments / EXP-004: LARS 3D Task Reasoning v1
section

EXP-004: LARS 3D Task Reasoning v1

Experiment 004 - LARS 3D Task Reasoning v1

Date: 2025-12-29 Status: Completed - SUCCESS

Configuration

  • Base Model: qwen2.5-7b-abliterated
  • Dataset: lars_3d_combined.json (20 examples: 12 identity + 8 tasks)
  • Format: 3D with and tags
  • Epochs: 10
  • Learning Rate: 3e-4
  • Max Length: 1024 tokens
  • Training Time: ~5 minutes

Results

  • Loss: 2.96 → 0.026 (excellent convergence)
  • Task Reasoning Test: 4/4 novel tasks handled with 3D format
  • Multi-step Planning: WORKING
  • Storage Decision: WORKING
  • Ambiguity Handling: WORKING

Novel Task Test Results

  1. 'Find that thing saved last week' → Reasoned about Context/KB search
  2. 'Check website redesign project' → Planned to search Track, create if missing
  3. 'Document this conversation' → Listed storage options, asked for clarification
  4. 'Which experiment worked best' → Planned to compare KPIs, identify metrics

Key Achievement

LARS now reasons through multi-step tasks, not just identity questions. The thinking process includes: - Breaking down vague requests - Identifying storage locations - Planning search operations - Handling ambiguity

Issues Found

  • Some hallucination (made up numbers like '18 experiments')
  • Base model knowledge mixing with trained knowledge
  • But: REASONING PATTERN is correct

Comparison to EXP-003

  • EXP-003: 12 examples, identity only → Identity works
  • EXP-004: 20 examples, identity + tasks → Tasks work too
  • Combined training preserves identity while adding capabilities

Output

  • Path: ~/corlera-training/outputs/lars-3d-v2-tasks
ID: dd98ec75 Path: Corlera AI Training Lab > Experiments > EXP-004: LARS 3D Task Reasoning v1 Updated: 2025-12-29T15:41:17