| Step 1 | loss:1.7985877990722656 lr:2.9999999999999997e-06 tokens_per_second_per_gpu:1555.8179337024162 | |
| Step 2 | loss:1.9999487400054932 lr:5.999999999999999e-06 tokens_per_second_per_gpu:1296.132338085489 | |
| Step 3 | loss:2.015929937362671 lr:8.999999999999999e-06 tokens_per_second_per_gpu:1380.3456940892718 | |
| Step 4 | loss:2.015044689178467 lr:1.1999999999999999e-05 tokens_per_second_per_gpu:1441.8579919070573 | |
| Step 5 | loss:1.902655005455017 lr:1.4999999999999999e-05 tokens_per_second_per_gpu:1496.5065650003771 | |
| Step 6 | loss:2.0002644062042236 lr:1.7999999999999997e-05 tokens_per_second_per_gpu:1284.2767002451735 | |
| Step 7 | loss:1.8712682723999023 lr:2.1e-05 tokens_per_second_per_gpu:1595.976345975988 | |
| Step 8 | loss:1.8941466808319092 lr:2.3999999999999997e-05 tokens_per_second_per_gpu:1465.6522512139272 | |
| Step 9 | loss:1.9504233598709106 lr:2.6999999999999996e-05 tokens_per_second_per_gpu:1549.7114254449693 | |
| Step 10 | loss:1.865391492843628 lr:2.9999999999999997e-05 tokens_per_second_per_gpu:1452.1724170387722 | |
| Step 11 | loss:1.9340863227844238 lr:3.2999999999999996e-05 tokens_per_second_per_gpu:1394.0622449308512 | |
| Step 12 | loss:1.8606351613998413 lr:3.5999999999999994e-05 tokens_per_second_per_gpu:1457.6889254299733 | |
| Step 13 | loss:1.779853343963623 lr:3.9e-05 tokens_per_second_per_gpu:1475.289790570931 | |
| Step 14 | loss:1.9142597913742065 lr:4.2e-05 tokens_per_second_per_gpu:1467.033586126942 | |
| Step 15 | loss:1.7863373756408691 lr:4.4999999999999996e-05 tokens_per_second_per_gpu:1528.426367918157 | |
| Step 16 | loss:1.8173195123672485 lr:4.7999999999999994e-05 tokens_per_second_per_gpu:1348.6580394777013 | |
| Step 17 | loss:1.8260715007781982 lr:5.1e-05 tokens_per_second_per_gpu:1412.9408605066283 | |
| Step 18 | loss:1.7154327630996704 lr:5.399999999999999e-05 tokens_per_second_per_gpu:1448.4773426179554 | |
| Step 19 | loss:1.6464484930038452 lr:5.6999999999999996e-05 tokens_per_second_per_gpu:1483.6856368571082 | |
| Step 20 | loss:1.7838977575302124 lr:5.9999999999999995e-05 tokens_per_second_per_gpu:1231.9379259494378 | |
| Step 21 | loss:1.565075159072876 lr:6.299999999999999e-05 tokens_per_second_per_gpu:1642.8062981888763 | |
| Step 22 | loss:1.5835440158843994 lr:6.599999999999999e-05 tokens_per_second_per_gpu:1346.9491692265267 | |
| Step 23 | loss:1.535355806350708 lr:6.9e-05 tokens_per_second_per_gpu:1492.6981358019466 | |
| Step 24 | loss:1.499534010887146 lr:7.199999999999999e-05 tokens_per_second_per_gpu:1582.5374859591595 | |
| Step 25 | loss:1.5575979948043823 lr:7.5e-05 tokens_per_second_per_gpu:1324.0694191136442 | |
| Step 26 | loss:1.5060899257659912 lr:7.8e-05 tokens_per_second_per_gpu:1489.3991698947707 | |
| Step 27 | loss:1.4290307760238647 lr:8.1e-05 tokens_per_second_per_gpu:1438.6956433735588 | |
| Step 28 | loss:1.5315165519714355 lr:8.4e-05 tokens_per_second_per_gpu:1516.4439634103949 | |
| Step 29 | loss:1.3571746349334717 lr:8.699999999999999e-05 tokens_per_second_per_gpu:1559.7452480397121 | |
| Step 30 | loss:1.3658448457717896 lr:8.999999999999999e-05 tokens_per_second_per_gpu:1624.000921530787 | |
| Step 31 | loss:1.4064968824386597 lr:9.3e-05 tokens_per_second_per_gpu:1470.7025159413279 | |
| Step 32 | loss:1.4688332080841064 lr:9.599999999999999e-05 tokens_per_second_per_gpu:1274.7291449115976 | |
| Step 33 | loss:1.318540334701538 lr:9.9e-05 tokens_per_second_per_gpu:1403.323757145447 | |
| Step 34 | loss:1.331732153892517 lr:0.000102 tokens_per_second_per_gpu:1439.3149399805036 | |
| Step 35 | loss:1.2614275217056274 lr:0.00010499999999999999 tokens_per_second_per_gpu:1408.4574407674436 | |
| Step 36 | loss:1.2727867364883423 lr:0.00010799999999999998 tokens_per_second_per_gpu:1494.8004940718877 | |
| Step 37 | loss:1.2808122634887695 lr:0.00011099999999999999 tokens_per_second_per_gpu:1457.0715465275755 | |
| Step 38 | loss:1.2685104608535767 lr:0.00011399999999999999 tokens_per_second_per_gpu:1443.0142558646523 | |
| Step 39 | loss:1.1761462688446045 lr:0.000117 tokens_per_second_per_gpu:1579.7090716301934 | |
| Step 40 | loss:1.147020936012268 lr:0.00011999999999999999 tokens_per_second_per_gpu:1330.2736989059222 | |
| Step 41 | loss:1.1341761350631714 lr:0.00012299999999999998 tokens_per_second_per_gpu:1573.5713952238086 | |
| Step 42 | loss:1.0792511701583862 lr:0.00012599999999999997 tokens_per_second_per_gpu:1386.653819015522 | |
| Step 43 | loss:1.0980397462844849 lr:0.000129 tokens_per_second_per_gpu:1386.150704960173 | |
| Step 44 | loss:1.05301034450531 lr:0.00013199999999999998 tokens_per_second_per_gpu:1480.1010677311333 | |
| Step 45 | loss:1.0550957918167114 lr:0.000135 tokens_per_second_per_gpu:1561.908295072645 | |
| Step 46 | loss:0.9554656147956848 lr:0.000138 tokens_per_second_per_gpu:1584.8598758505198 | |
| Step 47 | loss:1.0490007400512695 lr:0.00014099999999999998 tokens_per_second_per_gpu:1277.9966631180964 | |
| Step 48 | loss:0.98054039478302 lr:0.00014399999999999998 tokens_per_second_per_gpu:1496.1599456988538 | |
| Step 49 | loss:0.993450939655304 lr:0.000147 tokens_per_second_per_gpu:1489.6759872277803 | |
| Step 50 | loss:0.9852402210235596 lr:0.00015 tokens_per_second_per_gpu:1730.5556882365736 | |
| Step 51 | loss:0.9547162055969238 lr:0.00015299999999999998 tokens_per_second_per_gpu:1676.2263186208825 | |
| Step 52 | loss:0.9472491145133972 lr:0.000156 tokens_per_second_per_gpu:1497.8013605292456 | |
| Step 53 | loss:0.9579228162765503 lr:0.000159 tokens_per_second_per_gpu:1490.9087805618724 | |
| Step 54 | loss:0.9580035209655762 lr:0.000162 tokens_per_second_per_gpu:1358.2804213924767 | |
| Step 55 | loss:0.9533732533454895 lr:0.000165 tokens_per_second_per_gpu:1532.6439963514924 | |
| Step 56 | loss:0.946251392364502 lr:0.000168 tokens_per_second_per_gpu:1503.9021260510222 | |
| Step 57 | loss:0.9855115413665771 lr:0.00017099999999999998 tokens_per_second_per_gpu:1348.9810928821619 | |
| Step 58 | loss:0.9166429042816162 lr:0.00017399999999999997 tokens_per_second_per_gpu:1462.9679828950705 | |
| Step 59 | loss:0.9436288475990295 lr:0.00017699999999999997 tokens_per_second_per_gpu:1723.1953408430084 | |
| Step 60 | loss:0.9712100028991699 lr:0.00017999999999999998 tokens_per_second_per_gpu:1240.9568631929938 | |
| Step 61 | loss:0.9608094096183777 lr:0.00018299999999999998 tokens_per_second_per_gpu:1276.6036817145755 | |
| Step 62 | loss:0.9984250664710999 lr:0.000186 tokens_per_second_per_gpu:1453.4971988131354 | |
| Step 63 | loss:0.9865937829017639 lr:0.00018899999999999999 tokens_per_second_per_gpu:1347.1740115798698 | |
| Step 64 | loss:0.8917104005813599 lr:0.00019199999999999998 tokens_per_second_per_gpu:1300.5047312396237 | |
| Step 65 | loss:0.9269209504127502 lr:0.000195 tokens_per_second_per_gpu:1397.8605638036786 | |
| Step 66 | loss:0.9049241542816162 lr:0.000198 tokens_per_second_per_gpu:1557.1184943022347 | |
| Step 67 | loss:0.9827490448951721 lr:0.000201 tokens_per_second_per_gpu:1328.1302477120748 | |
| Step 68 | loss:0.947454035282135 lr:0.000204 tokens_per_second_per_gpu:1576.903412320162 | |
| Step 69 | loss:0.9214704036712646 lr:0.00020699999999999996 tokens_per_second_per_gpu:1347.060190630389 | |
| Step 70 | loss:0.9423002600669861 lr:0.00020999999999999998 tokens_per_second_per_gpu:1431.9273059290074 | |
| Step 71 | loss:0.9366826415061951 lr:0.00021299999999999997 tokens_per_second_per_gpu:1534.1645791395752 | |
| Step 72 | loss:0.981020450592041 lr:0.00021599999999999996 tokens_per_second_per_gpu:1551.8398185994226 | |
| Step 73 | loss:0.9794712662696838 lr:0.00021899999999999998 tokens_per_second_per_gpu:1479.186260504799 | |
| Step 74 | loss:0.8914351463317871 lr:0.00022199999999999998 tokens_per_second_per_gpu:1457.8753339923494 | |
| Step 75 | loss:0.9363726377487183 lr:0.000225 tokens_per_second_per_gpu:1328.366994491431 | |
| Step 76 | loss:0.9151436686515808 lr:0.00022799999999999999 tokens_per_second_per_gpu:1432.407802318865 | |
| Step 77 | loss:0.9868613481521606 lr:0.00023099999999999998 tokens_per_second_per_gpu:1607.8278549477732 | |
| Step 78 | loss:0.9109606146812439 lr:0.000234 tokens_per_second_per_gpu:1323.2506353596339 | |
| Step 79 | loss:0.9649548530578613 lr:0.000237 tokens_per_second_per_gpu:1528.7572159605845 | |
| Step 80 | loss:0.9578287601470947 lr:0.00023999999999999998 tokens_per_second_per_gpu:1600.9612077007519 | |
| Step 81 | loss:0.9568371176719666 lr:0.000243 tokens_per_second_per_gpu:1551.9491888234168 | |
| Step 82 | loss:0.9597994089126587 lr:0.00024599999999999996 tokens_per_second_per_gpu:1564.9121640595542 | |
| Step 83 | loss:0.9547963738441467 lr:0.000249 tokens_per_second_per_gpu:1381.7006758651535 | |
| Step 84 | loss:0.8862448334693909 lr:0.00025199999999999995 tokens_per_second_per_gpu:1466.4440918025123 | |
| Step 85 | loss:0.8928351998329163 lr:0.00025499999999999996 tokens_per_second_per_gpu:1316.4871058077088 | |
| Step 86 | loss:0.9270795583724976 lr:0.000258 tokens_per_second_per_gpu:1624.216943458876 | |
| Step 87 | loss:0.9267867803573608 lr:0.000261 tokens_per_second_per_gpu:1406.7079411261013 | |
| Step 88 | loss:0.9474061727523804 lr:0.00026399999999999997 tokens_per_second_per_gpu:1330.1561601282035 | |
| Step 89 | loss:0.9647872447967529 lr:0.000267 tokens_per_second_per_gpu:1475.5048043114116 | |
| Step 90 | loss:0.9821339845657349 lr:0.00027 tokens_per_second_per_gpu:1610.4988856920938 | |
| Step 91 | loss:0.9101476669311523 lr:0.00027299999999999997 tokens_per_second_per_gpu:1544.8735387609597 | |
| Step 92 | loss:0.8731852173805237 lr:0.000276 tokens_per_second_per_gpu:1178.3864094119626 | |
| Step 93 | loss:0.8970880508422852 lr:0.000279 tokens_per_second_per_gpu:1328.503949598527 | |
| Step 94 | loss:0.9337018132209778 lr:0.00028199999999999997 tokens_per_second_per_gpu:1646.5052853008472 | |
| Step 95 | loss:0.9561140537261963 lr:0.000285 tokens_per_second_per_gpu:1287.2284139648552 | |
| Step 96 | loss:0.8997252583503723 lr:0.00028799999999999995 tokens_per_second_per_gpu:1436.450444200157 | |
| Step 97 | loss:0.8851045966148376 lr:0.00029099999999999997 tokens_per_second_per_gpu:1472.231822985796 | |
| Step 98 | loss:0.8616557121276855 lr:0.000294 tokens_per_second_per_gpu:1359.8155094966787 | |
| Step 99 | loss:0.9687135815620422 lr:0.00029699999999999996 tokens_per_second_per_gpu:1320.0652759791772 | |
| Step 100 | loss:0.9114381670951843 lr:0.0003 tokens_per_second_per_gpu:1388.6744087905497 | |
| Step 101 | loss:0.9661620259284973 lr:0.0 tokens_per_second_per_gpu:1705.0146372092256 | |