Files
PS_only_answer_Qwen3-4B-Bas…/train_results.json

9 lines
233 B
JSON
Raw Normal View History

{
"epoch": 6.0,
"total_flos": 476005550456832.0,
"train_loss": 0.42957008274232433,
"train_runtime": 50642.7156,
"train_samples": 18626,
"train_samples_per_second": 2.207,
"train_steps_per_second": 0.011
}