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

8 lines
207 B
JSON
Raw Normal View History

{
"epoch": 1.0,
"total_flos": 1.939301794274345e+17,
"train_loss": 0.1304902312083122,
"train_runtime": 1065.8503,
"train_samples_per_second": 4.674,
"train_steps_per_second": 0.037
}