Files
SWE-Lego-Qwen3-4B-posttrain/all_results.json

8 lines
206 B
JSON
Raw Permalink Normal View History

{
"epoch": 4.0,
"total_flos": 2826281377071104.0,
"train_loss": 0.1602747890744274,
"train_runtime": 158332.2671,
"train_samples_per_second": 0.357,
"train_steps_per_second": 0.006
}