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

8 lines
206 B
JSON
Raw Permalink Normal View History

{
"total_flos": 20312064000.0,
"train_loss": 0.8405675888061523,
"train_runtime": 27.3869,
"train_samples": 6851,
"train_samples_per_second": 1.168,
"train_steps_per_second": 0.037
}