| Step 1 | loss:1.7985877990722656 lr:2.9999999999999997e-06 tokens_per_second_per_gpu:1548.4186911962104 | |
| Step 2 | loss:1.9999487400054932 lr:5.999999999999999e-06 tokens_per_second_per_gpu:1296.5932985903178 | |
| Step 3 | loss:2.0176382064819336 lr:8.999999999999999e-06 tokens_per_second_per_gpu:1382.6428800617155 | |
| Step 4 | loss:2.0169196128845215 lr:1.1999999999999999e-05 tokens_per_second_per_gpu:1444.2917484506193 | |
| Step 5 | loss:1.9037789106369019 lr:1.4999999999999999e-05 tokens_per_second_per_gpu:1497.0554968589836 | |
| Step 6 | loss:2.0014548301696777 lr:1.7999999999999997e-05 tokens_per_second_per_gpu:1286.7229109964867 | |
| Step 7 | loss:1.8709321022033691 lr:2.1e-05 tokens_per_second_per_gpu:1599.7738042768192 | |
| Step 8 | loss:1.8922226428985596 lr:2.3999999999999997e-05 tokens_per_second_per_gpu:1467.5629227354302 | |
| Step 9 | loss:1.9488790035247803 lr:2.6999999999999996e-05 tokens_per_second_per_gpu:1551.3215108623647 | |
| Step 10 | loss:1.8654146194458008 lr:2.9999999999999997e-05 tokens_per_second_per_gpu:1454.5651410119992 | |
| Step 11 | loss:1.935208797454834 lr:3.2999999999999996e-05 tokens_per_second_per_gpu:1395.3446497016182 | |
| Step 12 | loss:1.8592925071716309 lr:3.5999999999999994e-05 tokens_per_second_per_gpu:1461.588929942212 | |
| Step 13 | loss:1.77879798412323 lr:3.9e-05 tokens_per_second_per_gpu:1489.694861781623 | |
| Step 14 | loss:1.9113818407058716 lr:4.2e-05 tokens_per_second_per_gpu:1469.6248950125412 | |
| Step 15 | loss:1.7858730554580688 lr:4.4999999999999996e-05 tokens_per_second_per_gpu:1530.5904920259725 | |
| Step 16 | loss:1.8192064762115479 lr:4.7999999999999994e-05 tokens_per_second_per_gpu:1351.5487227344283 | |
| Step 17 | loss:1.8249778747558594 lr:5.1e-05 tokens_per_second_per_gpu:1413.7102660253827 | |
| Step 18 | loss:1.7167741060256958 lr:5.399999999999999e-05 tokens_per_second_per_gpu:1450.7358239498096 | |
| Step 19 | loss:1.6472349166870117 lr:5.6999999999999996e-05 tokens_per_second_per_gpu:1485.0740821331067 | |
| Step 20 | loss:1.7832927703857422 lr:5.9999999999999995e-05 tokens_per_second_per_gpu:1232.6498434827868 | |
| Step 21 | loss:1.5661098957061768 lr:6.299999999999999e-05 tokens_per_second_per_gpu:1644.7599298906832 | |
| Step 22 | loss:1.5848629474639893 lr:6.599999999999999e-05 tokens_per_second_per_gpu:1350.3085060056226 | |
| Step 23 | loss:1.5357799530029297 lr:6.9e-05 tokens_per_second_per_gpu:1494.9353972149197 | |
| Step 24 | loss:1.5002399682998657 lr:7.199999999999999e-05 tokens_per_second_per_gpu:1581.2856188375815 | |
| Step 25 | loss:1.5582427978515625 lr:7.5e-05 tokens_per_second_per_gpu:1328.5392444675613 | |
| Step 26 | loss:1.5054666996002197 lr:7.8e-05 tokens_per_second_per_gpu:1492.3639703369422 | |
| Step 27 | loss:1.4272029399871826 lr:8.1e-05 tokens_per_second_per_gpu:1439.4556259708406 | |
| Step 28 | loss:1.5300250053405762 lr:8.4e-05 tokens_per_second_per_gpu:1520.603916812337 | |
| Step 29 | loss:1.3552477359771729 lr:8.699999999999999e-05 tokens_per_second_per_gpu:1571.483048194161 | |
| Step 30 | loss:1.3640822172164917 lr:8.999999999999999e-05 tokens_per_second_per_gpu:1627.8488548342525 | |
| Step 31 | loss:1.4048514366149902 lr:9.3e-05 tokens_per_second_per_gpu:1472.726663454951 | |
| Step 32 | loss:1.466697335243225 lr:9.599999999999999e-05 tokens_per_second_per_gpu:1280.5256196823148 | |
| Step 33 | loss:1.3163751363754272 lr:9.9e-05 tokens_per_second_per_gpu:1406.43241714057 | |
| Step 34 | loss:1.3301761150360107 lr:0.000102 tokens_per_second_per_gpu:1443.1309938011434 | |
| Step 35 | loss:1.2589662075042725 lr:0.00010499999999999999 tokens_per_second_per_gpu:1411.2064652089884 | |
| Step 36 | loss:1.2690287828445435 lr:0.00010799999999999998 tokens_per_second_per_gpu:1496.8448470999326 | |
| Step 37 | loss:1.275730848312378 lr:0.00011099999999999999 tokens_per_second_per_gpu:1452.3096539685118 | |
| Step 38 | loss:1.2646681070327759 lr:0.00011399999999999999 tokens_per_second_per_gpu:1445.8747491857978 | |
| Step 39 | loss:1.1734347343444824 lr:0.000117 tokens_per_second_per_gpu:1583.1783418017678 | |
| Step 40 | loss:1.1434255838394165 lr:0.00011999999999999999 tokens_per_second_per_gpu:1334.9045716423566 | |
| Step 41 | loss:1.1307311058044434 lr:0.00012299999999999998 tokens_per_second_per_gpu:1568.6074809914642 | |
| Step 42 | loss:1.078163743019104 lr:0.00012599999999999997 tokens_per_second_per_gpu:1388.2485802639976 | |
| Step 43 | loss:1.0968904495239258 lr:0.000129 tokens_per_second_per_gpu:1390.0816878576202 | |
| Step 44 | loss:1.0498956441879272 lr:0.00013199999999999998 tokens_per_second_per_gpu:1481.7885028916617 | |
| Step 45 | loss:1.0517903566360474 lr:0.000135 tokens_per_second_per_gpu:1575.9811713763606 | |
| Step 46 | loss:0.9520314931869507 lr:0.000138 tokens_per_second_per_gpu:1589.3336475497715 | |
| Step 47 | loss:1.0399205684661865 lr:0.00014099999999999998 tokens_per_second_per_gpu:1280.4065012458989 | |
| Step 48 | loss:0.9798941612243652 lr:0.00014399999999999998 tokens_per_second_per_gpu:1490.0487592973677 | |
| Step 49 | loss:0.9811229705810547 lr:0.000147 tokens_per_second_per_gpu:1492.272358200793 | |
| Step 50 | loss:0.981967568397522 lr:0.00015 tokens_per_second_per_gpu:1733.0910729096504 | |
| Step 51 | loss:0.9523720741271973 lr:0.00015299999999999998 tokens_per_second_per_gpu:1680.0222107128054 | |
| Step 52 | loss:0.9394605159759521 lr:0.000156 tokens_per_second_per_gpu:1499.201746651047 | |
| Step 53 | loss:0.9593967795372009 lr:0.000159 tokens_per_second_per_gpu:1494.1725569389337 | |
| Step 54 | loss:0.9545915126800537 lr:0.000162 tokens_per_second_per_gpu:1359.551335095379 | |
| Step 55 | loss:0.9509159922599792 lr:0.000165 tokens_per_second_per_gpu:1534.5429811850474 | |
| Step 56 | loss:0.9438120722770691 lr:0.000168 tokens_per_second_per_gpu:1506.5267040683998 | |
| Step 57 | loss:0.9849022030830383 lr:0.00017099999999999998 tokens_per_second_per_gpu:1351.4279258551778 | |
| Step 58 | loss:0.9135311245918274 lr:0.00017399999999999997 tokens_per_second_per_gpu:1465.1256304549495 | |
| Step 59 | loss:0.9427099823951721 lr:0.00017699999999999997 tokens_per_second_per_gpu:1726.5320842362812 | |
| Step 60 | loss:0.9709662199020386 lr:0.00017999999999999998 tokens_per_second_per_gpu:1249.0799705740567 | |
| Step 61 | loss:0.9598491191864014 lr:0.00018299999999999998 tokens_per_second_per_gpu:1286.200798487998 | |
| Step 62 | loss:0.9993466138839722 lr:0.000186 tokens_per_second_per_gpu:1454.870705753997 | |
| Step 63 | loss:0.9856506586074829 lr:0.00018899999999999999 tokens_per_second_per_gpu:1348.4737261170767 | |
| Step 64 | loss:0.8916981220245361 lr:0.00019199999999999998 tokens_per_second_per_gpu:1304.2107312255102 | |
| Step 65 | loss:0.9262607097625732 lr:0.000195 tokens_per_second_per_gpu:1400.4956414804503 | |
| Step 66 | loss:0.9040940403938293 lr:0.000198 tokens_per_second_per_gpu:1558.1877234513206 | |
| Step 67 | loss:0.981691300868988 lr:0.000201 tokens_per_second_per_gpu:1332.2656621618937 | |
| Step 68 | loss:0.9467654824256897 lr:0.000204 tokens_per_second_per_gpu:1574.3130742177088 | |
| Step 69 | loss:0.9198861718177795 lr:0.00020699999999999996 tokens_per_second_per_gpu:1347.5136852252087 | |
| Step 70 | loss:0.9433321952819824 lr:0.00020999999999999998 tokens_per_second_per_gpu:1432.9845017702642 | |
| Step 71 | loss:0.9352939128875732 lr:0.00021299999999999997 tokens_per_second_per_gpu:1541.4846775305598 | |
| Step 72 | loss:0.9802192449569702 lr:0.00021599999999999996 tokens_per_second_per_gpu:1552.1371885005371 | |
| Step 73 | loss:0.9787095785140991 lr:0.00021899999999999998 tokens_per_second_per_gpu:1483.1991137563248 | |
| Step 74 | loss:0.8928729891777039 lr:0.00022199999999999998 tokens_per_second_per_gpu:1460.7259612378803 | |
| Step 75 | loss:0.9358883500099182 lr:0.000225 tokens_per_second_per_gpu:1330.5962121717346 | |
| Step 76 | loss:0.915272057056427 lr:0.00022799999999999999 tokens_per_second_per_gpu:1457.0449147843635 | |
| Step 77 | loss:0.9865199327468872 lr:0.00023099999999999998 tokens_per_second_per_gpu:1611.484956234028 | |
| Step 78 | loss:0.9116693139076233 lr:0.000234 tokens_per_second_per_gpu:1328.42239836243 | |
| Step 79 | loss:0.9653778076171875 lr:0.000237 tokens_per_second_per_gpu:1528.4796981175036 | |
| Step 80 | loss:0.956281304359436 lr:0.00023999999999999998 tokens_per_second_per_gpu:1601.7848666266386 | |
| Step 81 | loss:0.9559094309806824 lr:0.000243 tokens_per_second_per_gpu:1555.1940452499218 | |
| Step 82 | loss:0.9595820307731628 lr:0.00024599999999999996 tokens_per_second_per_gpu:1567.3686690510954 | |
| Step 83 | loss:0.9557052850723267 lr:0.000249 tokens_per_second_per_gpu:1382.082534165383 | |
| Step 84 | loss:0.8857594728469849 lr:0.00025199999999999995 tokens_per_second_per_gpu:1462.3701593010087 | |
| Step 85 | loss:0.8931686282157898 lr:0.00025499999999999996 tokens_per_second_per_gpu:1321.9620398390257 | |
| Step 86 | loss:0.9285029768943787 lr:0.000258 tokens_per_second_per_gpu:1624.5985801605502 | |
| Step 87 | loss:0.9276549220085144 lr:0.000261 tokens_per_second_per_gpu:1404.6117071486233 | |
| Step 88 | loss:0.9461902976036072 lr:0.00026399999999999997 tokens_per_second_per_gpu:1331.1508248461348 | |
| Step 89 | loss:0.9653772711753845 lr:0.000267 tokens_per_second_per_gpu:1476.6341498898312 | |
| Step 90 | loss:0.9833132028579712 lr:0.00027 tokens_per_second_per_gpu:1612.5973690157273 | |
| Step 91 | loss:0.9099349975585938 lr:0.00027299999999999997 tokens_per_second_per_gpu:1546.2912726399582 | |
| Step 92 | loss:0.8726711273193359 lr:0.000276 tokens_per_second_per_gpu:1189.798824625164 | |
| Step 93 | loss:0.8969229459762573 lr:0.000279 tokens_per_second_per_gpu:1344.051940180348 | |
| Step 94 | loss:0.9354563355445862 lr:0.00028199999999999997 tokens_per_second_per_gpu:1652.4346414576319 | |
| Step 95 | loss:0.9564660787582397 lr:0.000285 tokens_per_second_per_gpu:1292.180254295273 | |
| Step 96 | loss:0.9005736708641052 lr:0.00028799999999999995 tokens_per_second_per_gpu:1438.180978082653 | |
| Step 97 | loss:0.8859550952911377 lr:0.00029099999999999997 tokens_per_second_per_gpu:1475.158134702932 | |
| Step 98 | loss:0.862533688545227 lr:0.000294 tokens_per_second_per_gpu:1361.926083552786 | |
| Step 99 | loss:0.969555675983429 lr:0.00029699999999999996 tokens_per_second_per_gpu:1323.4095427897255 | |
| Step 100 | loss:0.9117950201034546 lr:0.0003 tokens_per_second_per_gpu:1391.4836543002448 | |
| Step 101 | loss:0.9669613838195801 lr:0.0 tokens_per_second_per_gpu:1706.952026192619 | |