Files
qwen3-8b-inpo-avg-eta0p005-s42/train_results.json

9 lines
216 B
JSON
Raw Permalink Normal View History

{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 9980.011584974314,
"train_runtime": 3282.8375,
"train_samples": 18644,
"train_samples_per_second": 5.679,
"train_steps_per_second": 0.044
}