| # Model arguments | |
| model_name_or_path: alignment-handbook/zephyr-7b-sft-full | |
| torch_dtype: null | |
| # Data training arguments | |
| # For definitions, see: src/h4/training/config.py | |
| dataset_mixer: | |
| HuggingFaceH4/ultrafeedback_binarized: 1.0 | |
| dataset_splits: | |
| - train_prefs | |
| - test_prefs | |
| preprocessing_num_workers: 12 | |
| # DPOTrainer arguments | |
| bf16: true | |
| beta: 0.01 | |
| do_eval: true | |
| eval_strategy: steps | |
| eval_steps: 100 | |
| gradient_accumulation_steps: 2 | |
| gradient_checkpointing: true | |
| gradient_checkpointing_kwargs: | |
| use_reentrant: False | |
| hub_model_id: zephyr-7b-dpo-full | |
| learning_rate: 5.0e-7 | |
| log_level: info | |
| logging_steps: 10 | |
| lr_scheduler_type: cosine | |
| max_length: 1024 | |
| max_prompt_length: 512 | |
| num_train_epochs: 1 | |
| optim: adamw_torch | |
| output_dir: data/zephyr-7b-dpo-full | |
| per_device_train_batch_size: 8 | |
| per_device_eval_batch_size: 8 | |
| push_to_hub: true | |
| save_strategy: "steps" | |
| save_steps: 100 | |
| save_total_limit: 1 | |
| seed: 42 | |
| warmup_ratio: 0.1 |