Files
HT-ht-analysis-Qwen-think-only/train_results.json

8 lines
207 B
JSON
Raw Permalink Normal View History

{
"epoch": 3.0,
"total_flos": 3129913528631296.0,
"train_loss": 0.36127943651608846,
"train_runtime": 259347.9359,
"train_samples_per_second": 0.917,
"train_steps_per_second": 0.038
}