qwen2-0.5b-instruct-simpo-lr-5e-07-gamma-1.5/train_results.json

{
    "epoch": 0.9981298423724285,
    "total_flos": 0.0,
    "train_loss": 1.7099600828689476,
    "train_runtime": 3104.7014,
    "train_samples": 59876,
    "train_samples_per_second": 19.286,
    "train_steps_per_second": 0.15
}