| { |
| "paths": { |
| "data_dir": "data", |
| "raw_dir": "data/raw", |
| "processed_dir": "data/processed", |
| "train_dir": "data/train", |
| "validation_dir": "data/validation", |
| "test_dir": "data/test", |
| "reports_dir": "reports", |
| "outputs_dir": "outputs" |
| }, |
| "data": { |
| "nl2bash_repo": "jiacheng-ye/nl2bash", |
| "linux_commands_repo": "mecha-org/linux-command-dataset", |
| "nl2bash_archive_url": "https://www.dropbox.com/s/wy7uahzbir7lrq1/nl2bash.zip?dl=1", |
| "min_instruction_chars": 5, |
| "min_command_chars": 2, |
| "max_instruction_chars": 600, |
| "max_command_chars": 600, |
| "head_command_cap": 2500, |
| "exact_command_cap": 40, |
| "near_duplicate_threshold": 0.9, |
| "drop_near_duplicates": false, |
| "split_grouping": "template", |
| "train_ratio": 0.9, |
| "validation_ratio": 0.05, |
| "test_ratio": 0.05, |
| "seed": 42 |
| }, |
| "model": { |
| "model_name": "LiquidAI/LFM2-700M", |
| "dtype": "bfloat16", |
| "attn_implementation": "sdpa", |
| "system_prompt": null, |
| "max_length": 128, |
| "trust_remote_code": false |
| }, |
| "lora": { |
| "r": 32, |
| "alpha": 64, |
| "dropout": 0.05, |
| "target_modules": [ |
| "q_proj", |
| "k_proj", |
| "v_proj", |
| "out_proj", |
| "w1", |
| "w2", |
| "w3", |
| "in_proj" |
| ], |
| "exclude_modules": [ |
| "conv.conv" |
| ], |
| "modules_to_save": [] |
| }, |
| "training": { |
| "method": "full", |
| "output_dir": "outputs/lfm2-linux-command", |
| "run_name": "lfm2-700m-linux-command", |
| "num_train_epochs": 3, |
| "per_device_train_batch_size": 16, |
| "per_device_eval_batch_size": 32, |
| "gradient_accumulation_steps": 2, |
| "learning_rate": 3e-05, |
| "lr_scheduler_type": "cosine", |
| "warmup_ratio": 0.03, |
| "weight_decay": 0.01, |
| "max_grad_norm": 1.0, |
| "optim": "adamw_torch_fused", |
| "adam_beta1": 0.9, |
| "adam_beta2": 0.95, |
| "adam_epsilon": 1e-08, |
| "bf16": true, |
| "fp16": false, |
| "gradient_checkpointing": false, |
| "group_by_length": true, |
| "logging_steps": 20, |
| "eval_strategy": "epoch", |
| "save_strategy": "epoch", |
| "save_total_limit": 2, |
| "load_best_model_at_end": true, |
| "metric_for_best_model": "eval_loss", |
| "greater_is_better": false, |
| "early_stopping_patience": 2, |
| "dataloader_num_workers": 4, |
| "seed": 42, |
| "report_to": [] |
| }, |
| "generation": { |
| "max_new_tokens": 128, |
| "do_sample": false, |
| "temperature": 1.0, |
| "top_p": 1.0, |
| "num_beams": 1, |
| "repetition_penalty": 1.0, |
| "batch_size": 32 |
| }, |
| "evaluation": { |
| "limit": null, |
| "execute_in_sandbox": false, |
| "sandbox_image": "linux-cmd-sandbox:latest", |
| "sandbox_timeout_s": 10, |
| "sandbox_memory": "256m", |
| "sandbox_cpus": "1.0", |
| "sandbox_pids_limit": 128, |
| "sandbox_network": false, |
| "max_execution_examples": 200 |
| } |
| } |
