87 lines
2.2 KiB
YAML
87 lines
2.2 KiB
YAML
|
top.booster: auto
|
||
|
|
top.checkpoint_path: []
|
||
|
|
top.finetuning_type: lora
|
||
|
|
top.model_name: Qwen3-1.7B-Base
|
||
|
|
top.quantization_bit: none
|
||
|
|
top.quantization_method: bnb
|
||
|
|
top.rope_scaling: none
|
||
|
|
top.template: default
|
||
|
|
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: 2
|
||
|
|
train.compute_type: bf16
|
||
|
|
train.create_new_adapter: false
|
||
|
|
train.cutoff_len: 2048
|
||
|
|
train.dataset:
|
||
|
|
- gpu_aiAgent_zh
|
||
|
|
- gpu_aiAgent_others
|
||
|
|
train.dataset_dir: data
|
||
|
|
train.ds_offload: false
|
||
|
|
train.ds_stage: none
|
||
|
|
train.enable_thinking: true
|
||
|
|
train.extra_args: '{"optim": "adamw_torch"}'
|
||
|
|
train.freeze_extra_modules: ''
|
||
|
|
train.freeze_language_model: false
|
||
|
|
train.freeze_multi_modal_projector: true
|
||
|
|
train.freeze_trainable_layers: 2
|
||
|
|
train.freeze_trainable_modules: all
|
||
|
|
train.freeze_vision_tower: true
|
||
|
|
train.galore_rank: 16
|
||
|
|
train.galore_scale: 2
|
||
|
|
train.galore_target: all
|
||
|
|
train.galore_update_interval: 200
|
||
|
|
train.gradient_accumulation_steps: 8
|
||
|
|
train.image_max_pixels: 768*768
|
||
|
|
train.image_min_pixels: 32*32
|
||
|
|
train.learning_rate: 5e-5
|
||
|
|
train.logging_steps: 5
|
||
|
|
train.lora_alpha: 128
|
||
|
|
train.lora_dropout: 0
|
||
|
|
train.lora_rank: 64
|
||
|
|
train.lora_target: ''
|
||
|
|
train.loraplus_lr_ratio: 0
|
||
|
|
train.lr_scheduler_type: cosine
|
||
|
|
train.mask_history: false
|
||
|
|
train.max_grad_norm: '1.0'
|
||
|
|
train.max_samples: '100000'
|
||
|
|
train.neat_packing: false
|
||
|
|
train.neftune_alpha: 0
|
||
|
|
train.num_train_epochs: '3.0'
|
||
|
|
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: 100
|
||
|
|
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.video_max_pixels: 256*256
|
||
|
|
train.video_min_pixels: 16*16
|
||
|
|
train.warmup_steps: 0
|