Proactive-Interactive-R1/Proactive-Interactive-R1-SFT-7B
017
1{2 "epoch": 3.0,3 "total_flos": 62777166004224.0,4 "train_loss": 1.4248257904052735,5 "train_runtime": 9087.8291,6 "train_samples_per_second": 1.32,7 "train_steps_per_second": 0.0418}