--- license: mit base_model: LiquidAI/LFM2.5-1.2B-Thinking tags: - meditation - reinforcement-learning - GRPO - QLoRA - math - reasoning pipeline_tag: text-generation --- # LFM2.5-1.2B-Meditation A fine-tuned version of [LiquidAI/LFM2.5-1.2B-Thinking](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking) trained with a novel **meditation** phase: self-supervised mathematical introspection inserted between SFT and task RL. ## Training Pipeline ## What is Meditation? Given a mathematical concept, the model produces a free-form exploration: restating concepts, probing edge cases, constructing examples/counterexamples, posing and solving novel problems, and synthesizing observations. This is scored by a composite reward: ## Checkpoints | File | Description | |------|-------------| | sft/sft.zip | SFT checkpoint (LoRA adapter, 42.4MB) | | meditation_rl/checkpoint-60.tar.gz | Meditation RL step 60 (training in progress) | ## Training Details - **Base model**: LFM2.5-1.2B-Thinking (1.17B dense, hybrid conv+attention) - **Method**: QLoRA (4-bit NF4, r=32, alpha=64, 22.2M trainable params) - **LoRA targets**: q_proj, k_proj, v_proj, out_proj, in_proj, w1, w2, w3 - **GRPO**: K=8 generations, LR 5e-7, KL beta 0.04 - **Judge**: Gemini 3.1 Pro Preview (paid API) - **Hardware**: Google Colab L4 (24GB VRAM, Ada Lovelace) - **Attention**: PyTorch SDPA (built-in), bf16 compute ## Current Metrics (Step 60) | Metric | Value | |--------|-------| | Reward mean | 0.43 | | KL divergence | 0.0009 | | Step time | 77s | | GPU memory | 3.7 / 22.5 GB | ## Dataset Training data: [Nirav-Madhani/meditation-math-seeds](https://huggingface.co/datasets/Nirav-Madhani/meditation-math-seeds) ## Paper Working paper available in the [repository](https://github.com/Nirav-Madhani/MeditationLearning).
