Files
open_reward_agent_qwen3_8b_…/train_results.json

8 lines
211 B
JSON
Raw Permalink Normal View History

{
"epoch": 3.0,
"total_flos": 2.5566761492312123e+20,
"train_loss": 0.34524431255128646,
"train_runtime": 116173.3714,
"train_samples_per_second": 2.973,
"train_steps_per_second": 0.023
}