train_results.json

{
    "achieved_tflops_per_gpu": 5.961135004994871,
    "achieved_tflops_per_gpu_theoretical": 528.5131118004142,
    "epoch": 7.0,
    "loss_nan_ranks": 0,
    "loss_rank_avg": 0.04253735765814781,
    "mfu_percent": 0.6027436809903812,
    "mfu_percent_theoretical": 53.439141739172314,
    "total_flos": 3.879727127867687e+18,
    "train_loss": 0.18411178431570632,
    "train_runtime": 81354.623,
    "train_samples_per_second": 2.497,
    "train_steps_per_second": 0.156,
    "valid_targets_mean": 4458.2,
    "valid_targets_min": 1268
}