Files
ronpo-qwen3-8b-fair-ht-mnpo…/all_results.json

9 lines
232 B
JSON
Raw Normal View History

{
"epoch": 0.8589835361488904,
"total_flos": 0.0,
"train_loss": 0.36845981503112446,
"train_runtime": 7265.877,
"train_samples": 16764,
"train_samples_per_second": 1.982,
"train_steps_per_second": 0.124
}