llama3-8b-base-new-method-q_t-0.4-s_star0.6/train_results.json

{
    "epoch": 0.9989528795811519,
    "total_flos": 0.0,
    "train_loss": 4.696330676288725,
    "train_runtime": 6071.6812,
    "train_samples": 61135,
    "train_samples_per_second": 10.069,
    "train_steps_per_second": 0.079
}