| top.booster: auto | |
| top.checkpoint_path: [] | |
| top.finetuning_type: lora | |
| top.model_name: Gemma-3-12B-Instruct | |
| top.quantization_bit: none | |
| top.quantization_method: bnb | |
| top.rope_scaling: none | |
| top.template: alpaca | |
| train.additional_target: '' | |
| train.apollo_rank: 16 | |
| train.apollo_scale: 32 | |
| train.apollo_target: all | |
| train.apollo_update_interval: 200 | |
| train.badam_mode: layer | |
| train.badam_switch_interval: 50 | |
| train.badam_switch_mode: ascending | |
| train.badam_update_ratio: 0.05 | |
| train.batch_size: 5 | |
| train.compute_type: bf16 | |
| train.create_new_adapter: true | |
| train.cutoff_len: 512 | |
| train.dataset: | |
| - top_5_training_dataset | |
| train.dataset_dir: data | |
| train.ds_offload: false | |
| train.ds_stage: none | |
| train.extra_args: '{"optim":"adamw_torch","weight_decay":0.01,"label_smoothing_factor":0.05}' | |
| train.freeze_extra_modules: '' | |
| train.freeze_trainable_layers: 4 | |
| train.freeze_trainable_modules: all | |
| train.galore_rank: 16 | |
| train.galore_scale: 2 | |
| train.galore_target: all | |
| train.galore_update_interval: 200 | |
| train.gradient_accumulation_steps: 5 | |
| train.learning_rate: 2e-5 | |
| train.logging_steps: 25 | |
| train.lora_alpha: 64 | |
| train.lora_dropout: 0.05 | |
| train.lora_rank: 32 | |
| train.lora_target: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj | |
| train.loraplus_lr_ratio: 8 | |
| train.lr_scheduler_type: cosine_with_restarts | |
| train.mask_history: false | |
| train.max_grad_norm: '0.3' | |
| train.max_samples: '100000' | |
| train.neat_packing: false | |
| train.neftune_alpha: 0 | |
| train.num_train_epochs: '4' | |
| train.packing: false | |
| train.ppo_score_norm: false | |
| train.ppo_whiten_rewards: false | |
| train.pref_beta: 0.1 | |
| train.pref_ftx: 0 | |
| train.pref_loss: sigmoid | |
| train.report_to: | |
| - none | |
| train.resize_vocab: false | |
| train.reward_model: [] | |
| train.save_steps: 250 | |
| train.swanlab_api_key: '' | |
| train.swanlab_link: '' | |
| train.swanlab_mode: cloud | |
| train.swanlab_project: llamafactory | |
| train.swanlab_run_name: '' | |
| train.swanlab_workspace: '' | |
| train.train_on_prompt: false | |
| train.training_stage: Supervised Fine-Tuning | |
| train.use_apollo: false | |
| train.use_badam: false | |
| train.use_dora: false | |
| train.use_galore: false | |
| train.use_llama_pro: false | |
| train.use_pissa: false | |
| train.use_rslora: false | |
| train.use_swanlab: false | |
| train.val_size: 0 | |
| train.warmup_steps: 150 | |