Files
qwen3-8b-aaai27-flagship-si…/train_results.json

9 lines
231 B
JSON
Raw Normal View History

{
"epoch": 0.8599068434252956,
"total_flos": 0.0,
"train_loss": 1.0422146828969319,
"train_runtime": 8158.2235,
"train_samples": 16746,
"train_samples_per_second": 1.765,
"train_steps_per_second": 0.11
}