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

8 lines
201 B
JSON
Raw Normal View History

{
"epoch": 3.0,
"total_flos": 16450670346240.0,
"train_loss": 1.665625898082319,
"train_runtime": 7008.0374,
"train_samples_per_second": 3.532,
"train_steps_per_second": 0.883
}