Files
qwen3-8B-sft-mix-v20250921-…/all_results.json

8 lines
203 B
JSON
Raw Normal View History

{
"epoch": 5.0,
"total_flos": 274293220966400.0,
"train_loss": 0.3892772012286716,
"train_runtime": 9724.0454,
"train_samples_per_second": 1.139,
"train_steps_per_second": 0.009
}