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

8 lines
210 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 2.4132193734570803e+17,
"train_loss": 0.08361149036965403,
"train_runtime": 1113.8618,
"train_samples_per_second": 16.871,
"train_steps_per_second": 0.132
}