base_model: Skywork/Skywork-Reward-V2-Qwen3-8B
model_type: AutoModelForSequenceClassification
num_labels: 1

reward_model: true
center_rewards_coefficient: 0.01  # Incentivize mean-zero rewards for improved stability
chat_template: qwen3
datasets:
  - path: argilla/distilabel-intel-orca-dpo-pairs
    type: bradley_terry.chat_template

val_set_size: 0.0
output_dir: ./outputs/out

sequence_len: 8192
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: true

deepspeed: deepspeed_configs/zero1.json

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 1
eval_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: linear
learning_rate: 0.00002

bf16: true
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
warmup_ratio: 0.1
logging_steps: 1
weight_decay: 0.01