train_results.json

{
    "epoch": 701.7610619469026,
    "num_input_tokens_seen": 23078128,
    "total_flos": 9.850767941652972e+17,
    "train_loss": 3.1605935114860535,
    "train_runtime": 11642.513,
    "train_samples_per_second": 13.743,
    "train_steps_per_second": 3.436
}