loss,grad_norm,learning_rate,epoch,step,train_runtime,train_samples_per_second,train_steps_per_second,total_flos,train_loss
0.5864,1.2203344106674194,3.8e-05,0.05060088551549652,20,,,,,
0.507,1.2138632535934448,3.974851100642631e-05,0.10120177103099304,40,,,,,
0.4975,1.2348554134368896,3.894753663431784e-05,0.15180265654648956,60,,,,,
0.4857,1.1599957942962646,3.761869351654803e-05,0.20240354206198607,80,,,,,
0.4817,1.2318143844604492,3.579900254735212e-05,0.2530044275774826,100,,,,,
0.4816,1.1294820308685303,3.35391593927652e-05,0.3036053130929791,120,,,,,
0.4766,1.1356878280639648,3.09021221351188e-05,0.35420619860847563,140,,,,,
0.4749,1.1366547346115112,2.7961357292848616e-05,0.40480708412397215,160,,,,,
0.4742,1.1533918380737305,2.479879308061041e-05,0.45540796963946867,180,,,,,
0.4712,1.1188915967941284,2.150253693083757e-05,0.5060088551549652,200,,,,,
0.469,1.1194959878921509,1.8164420865430394e-05,0.5566097406704618,220,,,,,
0.4623,1.0942271947860718,1.4877443102274734e-05,0.6072106261859582,240,,,,,
0.468,1.0687015056610107,1.1733177172132962e-05,0.6578115117014548,260,,,,,
0.4625,1.150633454322815,8.819220726594422e-06,0.7084123972169513,280,,,,,
0.4654,1.118627905845642,6.216755112000075e-06,0.7590132827324478,300,,,,,
0.4644,1.1107462644577026,3.9982836983718765e-06,0.8096141682479443,320,,,,,
0.4704,1.1417218446731567,2.22561197235428e-06,0.8602150537634409,340,,,,,
0.4673,1.1210877895355225,9.48125667752251e-07,0.9108159392789373,360,,,,,
0.4642,1.0706701278686523,2.0141490407443064e-07,0.9614168247944339,380,,,,,
,,,1.0,396,746.5624,67.74,0.53,7.531059569020416e+16,0.4799688560794098