Files
qwen3-8b-base-epsilon-dpo-h…/train_results.json

9 lines
230 B
JSON
Raw Normal View History

{
"epoch": 0.999244142101285,
"total_flos": 0.0,
"train_loss": 1.1906072249390895,
"train_runtime": 2288.3837,
"train_samples": 42336,
"train_samples_per_second": 18.5,
"train_steps_per_second": 0.289
}