epoch,step,train_loss 0,49,0.08183648437261581 0,99,0.1923932433128357 0,149,0.24491362273693085 0,199,0.0997917652130127 0,249,0.039667654782533646 0,299,0.095086008310318 0,349,0.18548668920993805 0,399,0.26539963483810425 0,449,0.043976228684186935 0,499,0.16827884316444397 1,549,0.23852306604385376 1,599,0.05851317197084427 1,649,0.10114896297454834 1,699,0.07927265763282776 1,749,0.10092920809984207 1,799,0.0028702891431748867 1,849,0.12155194580554962 1,899,0.06618201732635498 1,949,0.14083440601825714 1,999,0.06915386766195297 2,1049,0.13888002932071686 2,1099,0.014960141852498055 2,1149,0.10908274352550507 2,1199,0.09092564135789871 2,1249,0.13172835111618042 2,1299,0.03692478686571121 2,1349,0.2014639675617218 2,1399,0.02013213001191616 2,1449,0.14848573505878448 2,1499,0.04060028865933418 3,1549,0.03128346800804138 3,1599,0.09902003407478333 3,1649,0.003311517648398876 3,1699,0.04265011101961136 3,1749,0.0 3,1799,0.11723178625106812