Files
llama3-8b-full-pretrain-was…/all_results.json

8 lines
201 B
JSON
Raw Normal View History

{
"epoch": 3.0,
"total_flos": 3902317486080.0,
"train_loss": 1.6620939874066776,
"train_runtime": 1853.0016,
"train_samples_per_second": 3.081,
"train_steps_per_second": 0.771
}