Files
Qwen3-1.7B-Base-Openthought…/train_results.json

8 lines
206 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 5682852003840000.0,
"train_loss": 0.8983253232606124,
"train_runtime": 115389.9101,
"train_samples_per_second": 3.313,
"train_steps_per_second": 0.006
}