| model: | |
| model_config_path: configs/component4_model_config.yaml | |
| base_checkpoint_path: checkpoints/component5_420m/step_3200.pt | |
| tokenizer_dir: artifacts/tokenizer/code_tokenizer_v1 | |
| lora: | |
| r: 8 | |
| alpha: 16 | |
| dropout: 0.05 | |
| target_keywords: | |
| - q_proj | |
| - k_proj | |
| - v_proj | |
| - o_proj | |
| - fc1 | |
| - fc2 | |
| finetune: | |
| custom_data_path: data/raw/custom_finetune_pairs.jsonl | |
| output_dir: models/lora/custom_lora_v1 | |
| max_seq_len: 512 | |
| micro_batch_size: 1 | |
| grad_accum_steps: 16 | |
| learning_rate: 0.0003 | |
| weight_decay: 0.0 | |
| max_steps: 5 | |
| save_every: 5 | |
| eval_every: 5 | |
| early_stopping_patience_evals: 6 | |
| early_stopping_min_delta: 0.0005 | |
| use_fp16: true | |
| max_vram_gb: 7.0 | |
| resume: | |
| resume_from: none | |