step,epoch,event,loss,grad_norm,learning_rate,eval_loss,eval_accuracy,eval_precision,eval_recall,eval_f1,eval_runtime,eval_samples_per_second,eval_steps_per_second,train_runtime,train_samples_per_second,train_steps_per_second,total_flos,train_loss
10,0.04,log,0.7243,6.450088024139404,1.5000000000000002e-05,,,,,,,,,,,,,
20,0.08,log,0.6547,3.5925912857055664,1e-05,,,,,,,,,,,,,
20,0.08,log,,,,0.6500738263130188,0.61,0.6197183098591549,0.5365853658536586,0.5751633986928104,217.136,2.303,0.29,,,,,
20,0.08,evaluate,,,,0.6500738263130188,0.61,0.6197183098591549,0.5365853658536586,0.5751633986928104,217.136,2.303,0.29,,,,,
30,0.12,log,0.6126,8.919687271118164,5e-06,,,,,,,,,,,,,
40,0.16,log,0.6193,4.9131340980529785,0.0,,,,,,,,,,,,,
40,0.16,log,,,,0.6279698014259338,0.652,0.74,0.45121951219512196,0.5606060606060606,219.921,2.274,0.286,,,,,
40,0.16,evaluate,,,,0.6279698014259338,0.652,0.74,0.45121951219512196,0.5606060606060606,219.921,2.274,0.286,,,,,
40,0.16,log,,,,,,,,,,,,998.1872,0.321,0.04,21048884428800.0,0.652720320224762
50,0.2,log,0.5908,6.924829006195068,7.500000000000001e-06,,,,,,,,,,,,,
60,0.24,log,0.642,6.8762526512146,5e-06,,,,,,,,,,,,,
60,0.24,log,,,,0.5808247327804565,0.7,0.7608695652173914,0.5691056910569106,0.6511627906976745,227.7185,2.196,0.277,,,,,
60,0.24,evaluate,,,,0.5808247327804565,0.7,0.7608695652173914,0.5691056910569106,0.6511627906976745,227.7185,2.196,0.277,,,,,
70,0.28,log,0.5337,8.56165885925293,2.5e-06,,,,,,,,,,,,,
80,0.32,log,0.5653,6.879608631134033,0.0,,,,,,,,,,,,,
80,0.32,log,,,,0.5539242029190063,0.736,0.7435897435897436,0.7073170731707317,0.725,233.0561,2.145,0.27,,,,,
80,0.32,evaluate,,,,0.5539242029190063,0.736,0.7435897435897436,0.7073170731707317,0.725,233.0561,2.145,0.27,,,,,
80,0.32,log,,,,,,,,,,,,1023.5544,0.625,0.078,42097768857600.0,0.29147855639457704
80,0.32,log,,,,0.5539242029190063,0.736,0.7435897435897436,0.7073170731707317,0.725,243.0385,2.057,0.259,,,,,
80,0.32,evaluate,,,,0.5539242029190063,0.736,0.7435897435897436,0.7073170731707317,0.725,243.0385,2.057,0.259,,,,,