Files
Qwen1.5-MOE-sft-math7k-sft-…/train_results.json

8 lines
218 B
JSON
Raw Permalink Normal View History

{
"total_flos": 4.0376628208572826e+17,
"train_loss": 0.22927807642276896,
"train_runtime": 2180.6252,
"train_samples": 6851,
"train_samples_per_second": 6.284,
"train_steps_per_second": 0.197
}