train_hellaswag_101112_1760638083 / train_results.json
rbelanec's picture
End of training
4ab7eb6 verified
{
"epoch": 20.0,
"num_input_tokens_seen": 218373904,
"total_flos": 9.852512656423256e+18,
"train_loss": 0.015886625606237346,
"train_runtime": 78418.9489,
"train_samples_per_second": 9.16,
"train_steps_per_second": 2.29
}