Files
grpo-tool-sat-sft-qwen3-1p7…/train_results.json

8 lines
204 B
JSON
Raw Normal View History

{
"epoch": 2.0,
"total_flos": 7576988418048000.0,
"train_loss": 0.4733153915405273,
"train_runtime": 560.9841,
"train_samples_per_second": 28.521,
"train_steps_per_second": 1.783
}