| { |
| "model_id": "unsloth/Qwen2.5-1.5B-Instruct", |
| "training_algorithm": "ORPO", |
| "lora": { |
| "r": 16, |
| "lora_alpha": 32, |
| "target_modules": ["q_proj", "v_proj"], |
| "lora_dropout": 0.05, |
| "bias": "none", |
| "task_type": "CAUSAL_LM" |
| }, |
| "orpo_trainer": { |
| "learning_rate": 8e-6, |
| "per_device_train_batch_size": 2, |
| "gradient_accumulation_steps": 4, |
| "effective_batch_size": 8, |
| "num_train_epochs": 3, |
| "warmup_ratio": 0.1, |
| "lr_scheduler_type": "cosine", |
| "beta": 0.1, |
| "max_length": 1024, |
| "max_prompt_length": 512, |
| "logging_steps": 10, |
| "save_steps": 50, |
| "seed": 42 |
| }, |
| "precision": { |
| "bf16": false, |
| "fp16": true, |
| "note": "T4 GPU: fp16 only. Switch to bf16 on A100/4090." |
| }, |
| "adapter_output_dir": "training/adapter", |
| "hub_model_id": "rafiakedir/tenacious-bench-adapter", |
| "fixed_seed": 42, |
| "rationale": { |
| "orpo_vs_dpo": "ORPO chosen over DPO because it requires no reference model, reducing GPU memory footprint by ~40% on T4. Reference-free approach is appropriate for a judge component where the reference policy is undefined.", |
| "backbone_choice": "Qwen2.5-1.5B-Instruct selected per Prometheus-2 paper (Kim et al., 2024) showing 7B-class judge viability at 1.5B with preference tuning.", |
| "lora_rank": "Rank 16 with alpha 32 (2:1 ratio) is standard for task-specific adaptation. Rank 8 was considered but judge rubric complexity warrants higher rank.", |
| "beta_orpo": "Beta=0.1 follows ORPO paper (Hong et al., 2024) recommendation for instruction-following tasks." |
| } |
| } |
|
|
