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

# Model arguments
model_name_or_path: mistralai/Mistral-7B-v0.1
model_revision: main
torch_dtype: bfloat16
attn_implementation: flash_attention_2

# LoRA arguments
load_in_4bit: true
use_peft: true
lora_r: 16
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj

# Data training arguments
chat_template: "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}"
dataset_mixer:
  HuggingFaceH4/ultrachat_200k: 1.0
dataset_splits:
- train_sft
- test_sft
preprocessing_num_workers: 12

# SFT trainer config
bf16: true
do_eval: true
eval_strategy: epoch
gradient_accumulation_steps: 2
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
hub_model_id: zephyr-7b-sft-qlora
hub_strategy: every_save
learning_rate: 2.0e-04
log_level: info
logging_steps: 5  
logging_strategy: steps
lr_scheduler_type: cosine
max_seq_length: 2048
max_steps: -1
num_train_epochs: 1
output_dir: data/zephyr-7b-sft-qlora
overwrite_output_dir: true
per_device_eval_batch_size: 8
per_device_train_batch_size: 4
push_to_hub: true
report_to:
- tensorboard
save_strategy: "steps"
save_steps: 100
save_total_limit: 1
seed: 42
warmup_ratio: 0.1