step,epoch,loss,learning_rate,grad_norm,mean_token_accuracy 10,0.050793650793650794,1.5175626754760743,9.993914063644052e-05,0.2645105719566345,0.6436327129602433 20,0.10158730158730159,1.292062759399414,9.886131295443003e-05,0.1842157244682312,0.6806577108800411 30,0.1523809523809524,1.1331645011901856,9.646456421395446e-05,0.1463174968957901,0.7136855460703373 40,0.20317460317460317,1.0500896453857422,9.281359022841965e-05,0.15235942602157593,0.7293100193142891 50,0.25396825396825395,0.9814230918884277,8.800694230932884e-05,0.18486258387565613,0.7447394959628582 60,0.3047619047619048,0.9417718887329102,8.2174367055326e-05,0.20546093583106995,0.7523589514195919 70,0.35555555555555557,0.8714447975158691,7.547330408197695e-05,0.27494359016418457,0.7701701499521733 80,0.40634920634920635,0.8259673118591309,6.808463622961578e-05,0.2904492914676666,0.7822930864989758 90,0.45714285714285713,0.7809524536132812,6.0207806964560584e-05,0.6509429216384888,0.7934819318354129 100,0.5079365079365079,0.7385403633117675,5.205543677045049e-05,0.29676851630210876,0.804052384197712 110,0.5587301587301587,0.6973814964294434,4.384758385029457e-05,0.3625648319721222,0.8153482332825661 120,0.6095238095238096,0.6504372119903564,3.580580406099893e-05,0.3534400761127472,0.8266014747321606 130,0.6603174603174603,0.645383882522583,2.8147170421488272e-05,0.3655138909816742,0.8276743076741695 140,0.7111111111111111,0.6282196044921875,2.1078413626773546e-05,0.33809009194374084,0.8325855515897274 150,0.7619047619047619,0.602206802368164,1.4790341733986085e-05,0.3583182990550995,0.8397377617657185 160,0.8126984126984127,0.5957026004791259,9.452689650664515e-06,0.3788113296031952,0.8424368388950825 170,0.8634920634920635,0.5803478240966797,5.209537453863289e-06,0.34813615679740906,0.8462515577673912 180,0.9142857142857143,0.5834349155426025,2.1754212141102346e-06,0.3094688653945923,0.8446752935647964 190,0.9650793650793651,0.5862775802612304,4.322413053509944e-07,0.35028040409088135,0.8439742468297482