open-thoughts/OpenThinker-7B
1391k
1{2 "epoch": 2.9991577765300392,3 "total_flos": 4618853558517760.0,4 "train_loss": 0.43624040107819445,5 "train_runtime": 72959.568,6 "train_samples_per_second": 4.686,7 "train_steps_per_second": 0.0498}