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

8 lines
200 B
JSON
Raw Normal View History

{
"epoch": 3.0,
"total_flos": 8949330124800.0,
"train_loss": 1.6578803809801559,
"train_runtime": 3829.0681,
"train_samples_per_second": 3.476,
"train_steps_per_second": 0.87
}