Logic12/DeepSeek-R1-7B-RedMind
018
1{2 "epoch": 5.0,3 "total_flos": 1.565023977603072e+16,4 "train_loss": 3.387373956044515,5 "train_runtime": 55.9294,6 "train_samples_per_second": 3.218,7 "train_steps_per_second": 0.2688}1{2 "epoch": 5.0,3 "total_flos": 1.565023977603072e+16,4 "train_loss": 3.387373956044515,5 "train_runtime": 55.9294,6 "train_samples_per_second": 3.218,7 "train_steps_per_second": 0.2688}