Files
math-1b-sft-numinamath-bs51…/train_results.json

8 lines
207 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 7.06306771390772e+18,
"train_loss": 0.5769865204707152,
"train_runtime": 4593.0331,
"train_samples_per_second": 187.13,
"train_steps_per_second": 0.731
}