Files
Llama3.2-3B_Paper_Impact_da…/all_results.json

12 lines
350 B
JSON
Raw Normal View History

{
"epoch": 1.0,
"eval_loss": 0.09898750483989716,
"eval_runtime": 155.1758,
"eval_samples_per_second": 20.029,
"eval_steps_per_second": 0.632,
"total_flos": 1.8521361846213018e+17,
"train_loss": 0.11334303547354306,
"train_runtime": 974.5943,
"train_samples_per_second": 4.38,
"train_steps_per_second": 0.035
}