capsd-Qwen3-1.7B-Base-math_ppl_b4000_s0/all_results.json

{
    "epoch": 1.0,
    "total_flos": 2763503304704.0,
    "train_loss": 0.6990810878693111,
    "train_runtime": 502.9368,
    "train_samples_per_second": 7.953,
    "train_steps_per_second": 0.125
}