recipes/smollm2/dpo/config_smol.yaml

# Model arguments
model_name_or_path: loubnabnl/smollm2-360M-sft # we use this script for the 135M model too
torch_dtype: bfloat16

# 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: 0.5
do_eval: true
hub_private_repo: true
eval_strategy: steps
eval_steps: 100
gradient_accumulation_steps: 8
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: False
hub_model_id: smollm2-360M-dpo
learning_rate: 1.0e-6
log_level: info
logging_steps: 10
lr_scheduler_type: cosine
max_length: 1024
max_prompt_length: 512
num_train_epochs: 2
optim: adamw_torch
output_dir: data/smollm2-360M-dpo
per_device_train_batch_size: 2
per_device_eval_batch_size: 4
push_to_hub: true
report_to:
- tensorboard
- wandb
save_strategy: "no"
seed: 42
warmup_ratio: 0.1