Spaces:
Build error
Build error
| ### model | |
| model_name_or_path: Qwen/Qwen2-0.5B | |
| ### method | |
| stage: sft | |
| do_train: true | |
| finetuning_type: lora | |
| lora_target: all | |
| quantization_bit: 4 # use 4-bit QLoRA | |
| loraplus_lr_ratio: 16.0 # use LoRA+ with lambda=16.0 | |
| upcast_layernorm: true | |
| ### dataset | |
| dataset: mgtv_train | |
| template: qwen | |
| cutoff_len: 4096 | |
| max_samples: 25000 | |
| overwrite_cache: true | |
| preprocessing_num_workers: 16 | |
| ### output | |
| output_dir: saves/qwen2_0.5b/lora/sft_4bit | |
| logging_steps: 562 | |
| save_steps: 562 | |
| plot_loss: true | |
| # overwrite_output_dir: true | |
| # resume_from_checkpoint: true | |
| ### train | |
| per_device_train_batch_size: 8 | |
| gradient_accumulation_steps: 8 | |
| learning_rate: 1.0e-4 | |
| num_train_epochs: 3.0 | |
| lr_scheduler_type: cosine | |
| warmup_ratio: 0.1 | |
| bf16: true | |
| ddp_timeout: 180000000 | |
| ### eval | |
| val_size: 0.1 | |
| per_device_eval_batch_size: 1 | |
| eval_strategy: steps | |
| eval_steps: 562 | |
| report_to: none | |
| run_name: qwen2_0.5b # optional | |