train_results.json

{
    "achieved_tflops_per_gpu": 0.002083037344637663,
    "achieved_tflops_per_gpu_theoretical": 640.3139623735788,
    "epoch": 7.0,
    "loss_nan_ranks": 0,
    "loss_rank_avg": 0.2396668791770935,
    "mfu_percent": 0.000147211119762379,
    "mfu_percent_theoretical": 45.25187013240839,
    "total_flos": 688651439570944.0,
    "train_loss": 0.26112440031201767,
    "train_runtime": 20662.4788,
    "train_samples_per_second": 3.025,
    "train_steps_per_second": 0.189,
    "valid_targets_mean": 4082.4,
    "valid_targets_min": 866
}