Files
capsd-Qwen3-1.7B-Base-math_…/all_results.json

8 lines
200 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 1317930270720.0,
"train_loss": 0.7857931852340698,
"train_runtime": 252.6813,
"train_samples_per_second": 7.915,
"train_steps_per_second": 0.127
}