Files
Llama3.2-3B_Paper_Impact_co…/train_results.json

8 lines
208 B
JSON
Raw Normal View History

{
"epoch": 1.0,
"total_flos": 1.5530368955108557e+17,
"train_loss": 0.11576244132272129,
"train_runtime": 811.0761,
"train_samples_per_second": 4.543,
"train_steps_per_second": 0.036
}