all_results.json

{
    "epoch": 3.066,
    "eval_loss": 0.3744058609008789,
    "eval_masked_accuracy": 0.8805643239064613,
    "eval_perplexity": 1.454127204085947,
    "eval_runtime": 2.8656,
    "eval_samples_per_second": 1429.379,
    "eval_steps_per_second": 5.584,
    "num_parameters": 34149495.0,
    "total_flos": 9.74439612930639e+16,
    "train_loss": 0.6228721523284912,
    "train_runtime": 2832.8619,
    "train_samples_per_second": 2711.039,
    "train_samples_streaming": 7680000.0,
    "train_steps_per_second": 10.59
}