Files
qwen3-4b-safechain/train_results.json

8 lines
207 B
JSON
Raw Normal View History

{
"epoch": 2.0,
"total_flos": 2.46059940019431e+18,
"train_loss": 0.7171756315231324,
"train_runtime": 37151.4848,
"train_samples_per_second": 2.153,
"train_steps_per_second": 0.135
}