Files
Llama-3.1-8B-Instruct_SFT_s…/train_results.json

8 lines
218 B
JSON
Raw Normal View History

{
"total_flos": 2.091827002923077e+19,
"train_loss": 0.9512690712848968,
"train_runtime": 21456.929,
"train_samples": 145693,
"train_samples_per_second": 13.58,
"train_steps_per_second": 0.849
}