train_results.json

{
    "achieved_tflops_per_gpu": 3.6773450646115746,
    "achieved_tflops_per_gpu_theoretical": 389.6090247246643,
    "epoch": 7.0,
    "loss_nan_ranks": 0,
    "loss_rank_avg": 0.25698769092559814,
    "mfu_percent": 0.37182457680602377,
    "mfu_percent_theoretical": 39.39423910259498,
    "total_flos": 1.0409209055737283e+18,
    "train_loss": 0.5224247261221185,
    "train_runtime": 35382.8947,
    "train_samples_per_second": 1.835,
    "train_steps_per_second": 0.115,
    "valid_targets_mean": 3496.4,
    "valid_targets_min": 809
}