capsd-Qwen3-1.7B-Base-math_cap_b2000_s0/all_results.json

{
    "epoch": 1.0,
    "total_flos": 1655861018624.0,
    "train_loss": 0.4739113450050354,
    "train_runtime": 261.6357,
    "train_samples_per_second": 7.644,
    "train_steps_per_second": 0.122
}