recipes/zephyr-7b-beta/dpo/config_qlora.yaml

# Model arguments
model_name_or_path: alignment-handbook/zephyr-7b-sft-qlora
torch_dtype: bfloat16
attn_implementation: flash_attention_2

# LoRA arguments
use_peft: true
load_in_4bit: true
lora_r: 128
lora_alpha: 128
lora_dropout: 0.05
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj

# Data training arguments

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: 4
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
hub_model_id: zephyr-7b-dpo-qlora
learning_rate: 5.0e-6
log_level: info
logging_steps: 10
lr_scheduler_type: cosine
max_length: 1024
max_prompt_length: 512
num_train_epochs: 1
optim: paged_adamw_32bit
output_dir: data/zephyr-7b-dpo-qlora # It is handy to append `hub_model_revision` to keep track of your local experiments
per_device_train_batch_size: 4
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