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

8 lines
220 B
JSON
Raw Normal View History

{
"total_flos": 3.182940295913485e+19,
"train_loss": 1.0294154280057126,
"train_runtime": 32118.9012,
"train_samples": 145693,
"train_samples_per_second": 13.608,
"train_steps_per_second": 0.851
}