Files
Qwen2.5-7B-Instruct-R1-forf…/train_results.json

8 lines
203 B
JSON
Raw Permalink Normal View History

{
"epoch": 2.0,
"total_flos": 119307564613632.0,
"train_loss": 0.7332022241674937,
"train_runtime": 6450.9735,
"train_samples_per_second": 6.168,
"train_steps_per_second": 0.048
}