lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155
011
1{2 "epoch": 2.0,3 "total_flos": 2.1175585841610752e+17,4 "train_loss": 0.2914459398499242,5 "train_runtime": 58643.1461,6 "train_samples_per_second": 0.11,7 "train_steps_per_second": 0.0098}