train_results.json

{
    "epoch": 18.85902876001886,
    "num_input_tokens_seen": 37097424,
    "total_flos": 1.5834232254395843e+18,
    "train_loss": 0.33570288619101046,
    "train_runtime": 19776.3723,
    "train_samples_per_second": 8.09,
    "train_steps_per_second": 2.023
}