| step | total_steps | train | avg | val | train_tok_per_sec | total_sec |
| 1 | 100000 | 8.757771 | 8.757771 | 8.753775 | 1042.7 | 16.563 (0h) |
| 100 | 100000 | 7.683953 | 8.026178 | 7.674107 | 1114.7 | 1472.667 (0.4h) |
| 200 | 100000 | 7.066493 | 7.505785 | 7.120461 | 1117.7 | 2939.366 (0.8h) |
| 300 | 100000 | 6.539852 | 6.804404 | 6.690789 | 1119.4 | 4403.851 (1.2h) |
| 400 | 100000 | 6.281784 | 6.369585 | 6.377119 | 1127.2 | 5858.310 (1.6h) |
| 500 | 100000 | 5.991747 | 6.087850 | 6.184215 | 1130.2 | 7308.831 (2h) |
| 600 | 100000 | 5.668783 | 5.862515 | 5.992567 | 1126.2 | 8764.591 (2.4h) |
| 700 | 100000 | 5.613563 | 5.655438 | 5.860955 | 1127.4 | 10218.751 (2.8h) |
| 800 | 100000 | 5.513577 | 5.494509 | 5.679613 | 1121.7 | 11680.385 (3.2h) |
| 900 | 100000 | 5.291187 | 5.367141 | 5.563675 | 1120.2 | 13143.919 (3.7h) |
| 1000 | 100000 | 5.159078 | 5.189358 | 5.427361 | 1122.7 | 14604.215 (4.1h) |
| 1100 | 100000 | 4.960812 | 5.035579 | 5.302942 | 1121.2 | 16066.530 (4.5h) |
| 1200 | 100000 | 4.718549 | 4.884504 | 5.112857 | 1115.0 | 17536.973 (4.9h) |
| 1300 | 100000 | 4.726565 | 4.723352 | 5.008492 | 1120.4 | 19000.356 (5.3h) |
| 1400 | 100000 | 4.480641 | 4.601567 | 4.954243 | 1115.4 | 20470.156 (5.7h) |
| 1500 | 100000 | 4.465542 | 4.503632 | 4.853877 | 1118.6 | 21935.714 (6.1h) |
| 1600 | 100000 | 4.365374 | 4.390790 | 4.675542 | 1112.2 | 23409.788 (6.5h) |
| 1700 | 100000 | 4.227241 | 4.313663 | 4.606295 | 1113.5 | 24882.194 (6.9h) |
| 1800 | 100000 | 4.177152 | 4.230948 | 4.553156 | 1109.3 | 26360.174 (7.3h) |
| 1900 | 100000 | 4.261394 | 4.163821 | 4.518062 | 1105.2 | 27843.619 (7.7h) |
| 2000 | 100000 | 4.083753 | 4.111277 | 4.845702 | 1106.9 | 29324.546 (8.1h) |
| 2100 | 100000 | 4.004972 | 4.076214 | 4.447994 | 1107.5 | 30804.817 (8.6h) |
| 2200 | 100000 | 4.097307 | 4.026757 | 4.417393 | 1105.4 | 32287.935 (9h) |
| 2300 | 100000 | 3.870115 | 3.987558 | 4.810894 | 1102.0 | 33775.476 (9.4h) |
| 2400 | 100000 | 3.765733 | 3.957810 | 4.357313 | 1102.8 | 35262.042 (9.8h) |
| 2500 | 100000 | 3.881231 | 3.936353 | 4.336340 | 1103.8 | 36747.307 (10.2h) |
| 2600 | 100000 | 3.917612 | 3.908447 | 4.343965 | 1099.9 | 38237.698 (10.6h) |
| 2700 | 100000 | 3.900968 | 3.878037 | 4.510553 | 1097.1 | 39731.674 (11h) |
| 2800 | 100000 | 3.919621 | 3.863361 | 4.299088 | 1096.1 | 41227.347 (11.5h) |
| 2900 | 100000 | 3.863532 | 3.854397 | 4.997571 | 1096.1 | 42722.859 (11.9h) |
| 3000 | 100000 | 3.718850 | 3.815660 | 4.489297 | 1089.8 | 44226.966 (12.3h) |
| 3100 | 100000 | 3.839985 | 3.808275 | 4.378278 | 1091.1 | 45729.383 (12.7h) |
| 3200 | 100000 | 3.698415 | 3.767952 | 4.229772 | 1103.4 | 47215.175 (13.1h) |
| 3300 | 100000 | 3.577622 | 3.778669 | 4.620789 | 1097.7 | 48708.373 (13.5h) |
| 3400 | 100000 | 3.840034 | 3.763663 | 4.223394 | 1085.1 | 50219.250 (13.9h) |
| 3500 | 100000 | 3.808158 | 3.744361 | 4.222053 | 1077.4 | 51740.979 (14.4h) |
| 3501 | 13500 | 3.596871 | 3.596871 | 3.917194 | 988.7 | 4.808 (0h) |
| 3600 | 13500 | 3.646874 | 3.697564 | 3.863682 | 1050.5 | 391.622 (0.1h) |
| 3700 | 13500 | 3.690942 | 3.610765 | 3.824747 | 1050.5 | 782.390 (0.2h) |
| 3800 | 13500 | 3.601553 | 3.625615 | 3.809647 | 1029.8 | 1181.106 (0.3h) |
| 3900 | 13500 | 3.689713 | 3.633157 | 3.807812 | 1013.3 | 1586.218 (0.4h) |
| 4000 | 13500 | 3.152417 | 3.639959 | 4.344570 | 1045.4 | 1979.042 (0.5h) |
| 4100 | 13500 | 3.452450 | 3.648654 | 3.813874 | 1056.5 | 2367.405 (0.7h) |
| 4200 | 13500 | 3.580876 | 3.567281 | 4.324721 | 1056.9 | 2755.619 (0.8h) |
| 4300 | 13500 | 3.582937 | 3.582291 | 3.803398 | 1060.0 | 3142.920 (0.9h) |
| 4400 | 13500 | 3.466880 | 3.593686 | 3.811081 | 1059.2 | 3530.320 (1h) |
| 4500 | 13500 | 3.847186 | 3.594885 | 4.472014 | 1057.2 | 3918.523 (1.1h) |
| 4600 | 13500 | 3.654911 | 3.591510 | 3.785978 | 1061.7 | 4305.480 (1.2h) |
| 4700 | 13500 | 3.638580 | 3.537532 | 3.812144 | 1035.5 | 4701.717 (1.3h) |
| 4800 | 13500 | 3.641339 | 3.618926 | 3.775443 | 1034.3 | 5098.609 (1.4h) |
| 4900 | 13500 | 3.299883 | 3.570183 | 3.780090 | 1044.1 | 5491.823 (1.5h) |
| 5000 | 13500 | 3.450161 | 3.557157 | 3.777219 | 1057.0 | 5880.027 (1.6h) |
| 5100 | 13500 | 3.620585 | 3.555069 | 3.776788 | 1056.8 | 6268.260 (1.7h) |
| 5200 | 13500 | 3.687817 | 3.544722 | 5.507851 | 1066.4 | 6653.064 (1.8h) |
| 5300 | 13500 | 3.420722 | 3.470167 | 3.985136 | 1044.3 | 7045.963 (2h) |
| 5400 | 13500 | 3.469401 | 3.545307 | 3.749447 | 1061.2 | 7432.861 (2.1h) |
| 5500 | 13500 | 3.131010 | 3.564215 | 3.743536 | 1057.6 | 7821.067 (2.2h) |
| 5600 | 13500 | 3.529708 | 3.516260 | 4.250351 | 1064.0 | 8206.682 (2.3h) |
| 5700 | 13500 | 3.431514 | 3.522448 | 3.724683 | 1057.6 | 8594.914 (2.4h) |
| 5800 | 13500 | 3.670563 | 3.532795 | 3.724966 | 1052.5 | 8984.718 (2.5h) |
| 5900 | 13500 | 3.396939 | 3.562216 | 4.290133 | 1063.3 | 9370.607 (2.6h) |
| 6000 | 13500 | 3.536122 | 3.543687 | 3.726020 | 1063.8 | 9756.391 (2.7h) |
| 6100 | 13500 | 3.339090 | 3.515912 | 3.746930 | 1061.7 | 10142.976 (2.8h) |
| 6200 | 13500 | 3.609086 | 3.501728 | 3.816966 | 1062.4 | 10529.225 (2.9h) |
| 6300 | 13500 | 3.701195 | 3.521127 | 3.726227 | 1061.9 | 10915.699 (3h) |
| 6400 | 13500 | 3.632363 | 3.519309 | 3.729982 | 1066.4 | 11300.527 (3.1h) |
| 6500 | 13500 | 3.613995 | 3.486497 | 3.732116 | 1040.4 | 11694.950 (3.2h) |
| 6600 | 13500 | 3.574078 | 3.527788 | 3.706010 | 1067.0 | 12079.732 (3.4h) |
| 6700 | 13500 | 3.563777 | 3.515896 | 3.711095 | 1066.8 | 12464.365 (3.5h) |
| 6800 | 13500 | 3.663382 | 3.511864 | 3.700980 | 1067.7 | 12848.875 (3.6h) |
| 6900 | 13500 | 3.515339 | 3.446972 | 3.697517 | 1067.0 | 13233.616 (3.7h) |
| 7000 | 13500 | 3.119249 | 3.478116 | 3.706401 | 1064.7 | 13619.038 (3.8h) |
| 7100 | 13500 | 3.458316 | 3.496225 | 3.693866 | 1061.1 | 14005.879 (3.9h) |
| 7200 | 13500 | 3.681320 | 3.453815 | 3.694162 | 1058.5 | 14393.540 (4h) |
| 7202 | 13500 | 3.668970 | 3.620950 | 3.693406 | 1047.4 | 14402.343 (4h) |
| 7203 | 7702 | 5.184289 | 5.184289 | 4.910613 | 1028.2 | 8.766 (0h) |
| 7225 | 7702 | 3.922032 | 4.611678 | 3.684422 | 1074.1 | 177.804 (0h) |
| 7250 | 7702 | 2.851829 | 3.287994 | 2.675251 | 1031.5 | 377.537 (0.1h) |
| 7275 | 7702 | 2.253387 | 2.517715 | 2.209526 | 1050.1 | 573.591 (0.2h) |
| 7300 | 7702 | 1.853095 | 2.083367 | 4.671023 | 1025.7 | 774.082 (0.2h) |
| 7325 | 7702 | 1.771890 | 1.817792 | 1.742239 | 1029.0 | 974.347 (0.3h) |
| 7350 | 7702 | 1.705379 | 1.659719 | 1.704938 | 1029.8 | 1174.445 (0.3h) |
| 7375 | 7702 | 1.517625 | 1.571185 | 1.695838 | 1097.5 | 1362.014 (0.4h) |
| 7400 | 7702 | 1.461409 | 1.493062 | 1.693709 | 1067.4 | 1554.867 (0.4h) |
| 7425 | 7702 | 1.478858 | 1.441712 | 1.700632 | 1105.2 | 1741.003 (0.5h) |
| 7450 | 7702 | 1.403970 | 1.412704 | 1.706673 | 1065.5 | 1934.008 (0.5h) |
| 7475 | 7702 | 1.347545 | 1.345179 | 1.714350 | 1059.3 | 2128.123 (0.6h) |
| 7500 | 7702 | 1.371548 | 1.319142 | 3.382941 | 1101.3 | 2314.901 (0.6h) |