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

9 lines
230 B
JSON
Raw Normal View History

{
"epoch": 0.8599068434252956,
"total_flos": 0.0,
"train_loss": 4429.094605034722,
"train_runtime": 7055.131,
"train_samples": 16746,
"train_samples_per_second": 2.041,
"train_steps_per_second": 0.128
}