Files
gemma-3-1b-it_SFT_mathv00.03/all_results.json

8 lines
219 B
JSON
Raw Normal View History

{
"total_flos": 6.428081412041081e+18,
"train_loss": 0.6103494446655175,
"train_runtime": 7328.7514,
"train_samples": 125770,
"train_samples_per_second": 51.484,
"train_steps_per_second": 0.402
}