Files
Caracal_GPT/train_results.json

8 lines
223 B
JSON
Raw Normal View History

{
"epoch": 3.999907537967222,
"total_flos": 2.2497279214378476e+18,
"train_loss": 2.3588384375217277,
"train_runtime": 26949.388,
"train_samples_per_second": 205.47,
"train_steps_per_second": 1.605
}