open_reward_agent_qwen3_8b_sft_v1/all_results.json

{
    "epoch": 3.0,
    "total_flos": 2.5566761492312123e+20,
    "train_loss": 0.34524431255128646,
    "train_runtime": 116173.3714,
    "train_samples_per_second": 2.973,
    "train_steps_per_second": 0.023
}