eval_results.json

{
    "eval_reasoning_loss": 0.8222787380218506,
    "eval_reasoning_runtime": 27.3158,
    "eval_reasoning_samples_per_second": 4.723,
    "eval_reasoning_steps_per_second": 1.208,
    "eval_samples": 100,
    "eval_utility_loss": 1.4264225959777832,
    "eval_utility_runtime": 10.2998,
    "eval_utility_samples_per_second": 4.757,
    "eval_utility_steps_per_second": 1.262
}