{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 3093, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.009699321047526674, "grad_norm": 1.020737016686291, "learning_rate": 1.0752688172043011e-06, "loss": 0.3895, "step": 10 }, { "epoch": 0.019398642095053348, "grad_norm": 0.7534117886463607, "learning_rate": 2.1505376344086023e-06, "loss": 0.3209, "step": 20 }, { "epoch": 0.029097963142580018, "grad_norm": 0.4377375711052428, "learning_rate": 3.225806451612903e-06, "loss": 0.2648, "step": 30 }, { "epoch": 0.038797284190106696, "grad_norm": 0.3125953720371267, "learning_rate": 4.3010752688172045e-06, "loss": 0.2353, "step": 40 }, { "epoch": 0.04849660523763336, "grad_norm": 0.26931955183857703, "learning_rate": 5.376344086021506e-06, "loss": 0.2211, "step": 50 }, { "epoch": 0.058195926285160036, "grad_norm": 0.26461533217537725, "learning_rate": 6.451612903225806e-06, "loss": 0.2065, "step": 60 }, { "epoch": 0.06789524733268672, "grad_norm": 0.8264176079441389, "learning_rate": 7.526881720430108e-06, "loss": 0.2, "step": 70 }, { "epoch": 0.07759456838021339, "grad_norm": 0.2983222843388067, "learning_rate": 8.602150537634409e-06, "loss": 0.1932, "step": 80 }, { "epoch": 0.08729388942774007, "grad_norm": 0.581254385336681, "learning_rate": 9.67741935483871e-06, "loss": 0.1888, "step": 90 }, { "epoch": 0.09699321047526673, "grad_norm": 0.3121423374050484, "learning_rate": 9.999865664319414e-06, "loss": 0.186, "step": 100 }, { "epoch": 0.1066925315227934, "grad_norm": 0.2650187228146991, "learning_rate": 9.999207711016081e-06, "loss": 0.182, "step": 110 }, { "epoch": 0.11639185257032007, "grad_norm": 0.26944373713294145, "learning_rate": 9.998001538251283e-06, "loss": 0.1779, "step": 120 }, { "epoch": 0.12609117361784675, "grad_norm": 0.32148775806687896, "learning_rate": 9.99624727829546e-06, "loss": 0.1743, "step": 130 }, { "epoch": 0.13579049466537343, "grad_norm": 0.23147855380574123, "learning_rate": 9.99394512352298e-06, "loss": 0.176, "step": 140 }, { "epoch": 0.1454898157129001, "grad_norm": 0.5006127662496982, "learning_rate": 9.991095326391061e-06, "loss": 0.1741, "step": 150 }, { "epoch": 0.15518913676042678, "grad_norm": 0.4320980518392451, "learning_rate": 9.98769819941207e-06, "loss": 0.1702, "step": 160 }, { "epoch": 0.16488845780795344, "grad_norm": 0.3889487478872514, "learning_rate": 9.983754115119262e-06, "loss": 0.1727, "step": 170 }, { "epoch": 0.17458777885548013, "grad_norm": 0.27135352703963794, "learning_rate": 9.97926350602593e-06, "loss": 0.1701, "step": 180 }, { "epoch": 0.1842870999030068, "grad_norm": 0.25440030820854326, "learning_rate": 9.97422686457796e-06, "loss": 0.1678, "step": 190 }, { "epoch": 0.19398642095053345, "grad_norm": 0.236255441704788, "learning_rate": 9.968644743099848e-06, "loss": 0.1641, "step": 200 }, { "epoch": 0.20368574199806014, "grad_norm": 0.45878670927299864, "learning_rate": 9.96251775373412e-06, "loss": 0.167, "step": 210 }, { "epoch": 0.2133850630455868, "grad_norm": 0.22778682431164834, "learning_rate": 9.955846568374201e-06, "loss": 0.1655, "step": 220 }, { "epoch": 0.22308438409311349, "grad_norm": 0.23943633515604867, "learning_rate": 9.948631918590746e-06, "loss": 0.1617, "step": 230 }, { "epoch": 0.23278370514064015, "grad_norm": 0.24350940452858558, "learning_rate": 9.940874595551403e-06, "loss": 0.1626, "step": 240 }, { "epoch": 0.24248302618816683, "grad_norm": 0.22335875945360728, "learning_rate": 9.932575449934063e-06, "loss": 0.1644, "step": 250 }, { "epoch": 0.2521823472356935, "grad_norm": 0.23496059802926855, "learning_rate": 9.923735391833564e-06, "loss": 0.1618, "step": 260 }, { "epoch": 0.2618816682832202, "grad_norm": 0.22613625236616156, "learning_rate": 9.914355390661897e-06, "loss": 0.1588, "step": 270 }, { "epoch": 0.27158098933074687, "grad_norm": 0.28310779926466306, "learning_rate": 9.904436475041892e-06, "loss": 0.1599, "step": 280 }, { "epoch": 0.2812803103782735, "grad_norm": 0.23716946411046663, "learning_rate": 9.893979732694422e-06, "loss": 0.1608, "step": 290 }, { "epoch": 0.2909796314258002, "grad_norm": 0.22939002583419776, "learning_rate": 9.882986310319124e-06, "loss": 0.1571, "step": 300 }, { "epoch": 0.3006789524733269, "grad_norm": 0.1829019556630992, "learning_rate": 9.871457413468645e-06, "loss": 0.1602, "step": 310 }, { "epoch": 0.31037827352085356, "grad_norm": 0.2862249824823463, "learning_rate": 9.859394306416443e-06, "loss": 0.1587, "step": 320 }, { "epoch": 0.3200775945683802, "grad_norm": 0.1916670538928815, "learning_rate": 9.846798312018147e-06, "loss": 0.1593, "step": 330 }, { "epoch": 0.3297769156159069, "grad_norm": 0.19602376121876022, "learning_rate": 9.833670811566485e-06, "loss": 0.1555, "step": 340 }, { "epoch": 0.3394762366634336, "grad_norm": 0.24177047491392098, "learning_rate": 9.820013244639817e-06, "loss": 0.1575, "step": 350 }, { "epoch": 0.34917555771096026, "grad_norm": 0.1876075373970573, "learning_rate": 9.80582710894426e-06, "loss": 0.1573, "step": 360 }, { "epoch": 0.3588748787584869, "grad_norm": 0.2927139950691107, "learning_rate": 9.791113960149458e-06, "loss": 0.1549, "step": 370 }, { "epoch": 0.3685741998060136, "grad_norm": 0.24672228818761555, "learning_rate": 9.775875411717981e-06, "loss": 0.1559, "step": 380 }, { "epoch": 0.37827352085354027, "grad_norm": 0.25633769481093877, "learning_rate": 9.760113134728383e-06, "loss": 0.156, "step": 390 }, { "epoch": 0.3879728419010669, "grad_norm": 0.22368063952475076, "learning_rate": 9.743828857691964e-06, "loss": 0.1549, "step": 400 }, { "epoch": 0.3976721629485936, "grad_norm": 0.42577732642751726, "learning_rate": 9.727024366363208e-06, "loss": 0.1546, "step": 410 }, { "epoch": 0.4073714839961203, "grad_norm": 0.30290230685059993, "learning_rate": 9.709701503543954e-06, "loss": 0.1541, "step": 420 }, { "epoch": 0.41707080504364696, "grad_norm": 0.19793407217815825, "learning_rate": 9.691862168881325e-06, "loss": 0.153, "step": 430 }, { "epoch": 0.4267701260911736, "grad_norm": 0.21683658128298464, "learning_rate": 9.673508318659399e-06, "loss": 0.1514, "step": 440 }, { "epoch": 0.4364694471387003, "grad_norm": 0.2542785033568332, "learning_rate": 9.65464196558468e-06, "loss": 0.1507, "step": 450 }, { "epoch": 0.44616876818622697, "grad_norm": 0.18399976352178382, "learning_rate": 9.635265178565386e-06, "loss": 0.1529, "step": 460 }, { "epoch": 0.45586808923375366, "grad_norm": 0.16248682082363208, "learning_rate": 9.615380082484573e-06, "loss": 0.1524, "step": 470 }, { "epoch": 0.4655674102812803, "grad_norm": 0.24408305032393154, "learning_rate": 9.594988857967107e-06, "loss": 0.1519, "step": 480 }, { "epoch": 0.475266731328807, "grad_norm": 0.24001150201316104, "learning_rate": 9.574093741140549e-06, "loss": 0.1503, "step": 490 }, { "epoch": 0.48496605237633367, "grad_norm": 0.21337935060277946, "learning_rate": 9.552697023389923e-06, "loss": 0.15, "step": 500 }, { "epoch": 0.49466537342386036, "grad_norm": 0.17464159632335755, "learning_rate": 9.530801051106449e-06, "loss": 0.1505, "step": 510 }, { "epoch": 0.504364694471387, "grad_norm": 0.16833615600888802, "learning_rate": 9.508408225430237e-06, "loss": 0.1512, "step": 520 }, { "epoch": 0.5140640155189137, "grad_norm": 0.18834381819632562, "learning_rate": 9.485521001986961e-06, "loss": 0.1438, "step": 530 }, { "epoch": 0.5237633365664404, "grad_norm": 0.20243272397310594, "learning_rate": 9.46214189061859e-06, "loss": 0.1513, "step": 540 }, { "epoch": 0.533462657613967, "grad_norm": 0.200191598724974, "learning_rate": 9.438273455108145e-06, "loss": 0.1489, "step": 550 }, { "epoch": 0.5431619786614937, "grad_norm": 0.16174114410966278, "learning_rate": 9.41391831289855e-06, "loss": 0.1496, "step": 560 }, { "epoch": 0.5528612997090203, "grad_norm": 0.3626796052816055, "learning_rate": 9.38907913480561e-06, "loss": 0.1457, "step": 570 }, { "epoch": 0.562560620756547, "grad_norm": 0.18785993468756543, "learning_rate": 9.36375864472511e-06, "loss": 0.1443, "step": 580 }, { "epoch": 0.5722599418040737, "grad_norm": 0.17772800871532357, "learning_rate": 9.337959619334125e-06, "loss": 0.1476, "step": 590 }, { "epoch": 0.5819592628516004, "grad_norm": 0.15601447310629252, "learning_rate": 9.31168488778652e-06, "loss": 0.1476, "step": 600 }, { "epoch": 0.5916585838991271, "grad_norm": 0.19821208464194934, "learning_rate": 9.284937331402697e-06, "loss": 0.1468, "step": 610 }, { "epoch": 0.6013579049466538, "grad_norm": 0.19029097473240159, "learning_rate": 9.25771988335363e-06, "loss": 0.1482, "step": 620 }, { "epoch": 0.6110572259941804, "grad_norm": 0.18175837679945547, "learning_rate": 9.230035528339212e-06, "loss": 0.1455, "step": 630 }, { "epoch": 0.6207565470417071, "grad_norm": 0.18340667052442786, "learning_rate": 9.201887302260943e-06, "loss": 0.1485, "step": 640 }, { "epoch": 0.6304558680892337, "grad_norm": 0.15339041315406826, "learning_rate": 9.173278291889016e-06, "loss": 0.1466, "step": 650 }, { "epoch": 0.6401551891367604, "grad_norm": 0.15699088899673416, "learning_rate": 9.14421163452381e-06, "loss": 0.1466, "step": 660 }, { "epoch": 0.6498545101842871, "grad_norm": 0.24981887731533495, "learning_rate": 9.11469051765186e-06, "loss": 0.1464, "step": 670 }, { "epoch": 0.6595538312318138, "grad_norm": 0.16649549015322454, "learning_rate": 9.084718178596301e-06, "loss": 0.1452, "step": 680 }, { "epoch": 0.6692531522793405, "grad_norm": 0.16481654938724005, "learning_rate": 9.054297904161868e-06, "loss": 0.1439, "step": 690 }, { "epoch": 0.6789524733268671, "grad_norm": 0.24499406154651857, "learning_rate": 9.02343303027446e-06, "loss": 0.1465, "step": 700 }, { "epoch": 0.6886517943743938, "grad_norm": 0.1496332910263056, "learning_rate": 8.992126941615314e-06, "loss": 0.1458, "step": 710 }, { "epoch": 0.6983511154219205, "grad_norm": 0.16548997088070388, "learning_rate": 8.960383071249837e-06, "loss": 0.1451, "step": 720 }, { "epoch": 0.7080504364694471, "grad_norm": 0.20683623207389146, "learning_rate": 8.928204900251136e-06, "loss": 0.1452, "step": 730 }, { "epoch": 0.7177497575169738, "grad_norm": 0.20126316747636905, "learning_rate": 8.895595957318277e-06, "loss": 0.146, "step": 740 }, { "epoch": 0.7274490785645005, "grad_norm": 0.14334846077395094, "learning_rate": 8.862559818389322e-06, "loss": 0.1418, "step": 750 }, { "epoch": 0.7371483996120272, "grad_norm": 0.17612864303411396, "learning_rate": 8.829100106249189e-06, "loss": 0.1429, "step": 760 }, { "epoch": 0.7468477206595538, "grad_norm": 0.15223827251186925, "learning_rate": 8.795220490132369e-06, "loss": 0.1461, "step": 770 }, { "epoch": 0.7565470417070805, "grad_norm": 0.17586006541625654, "learning_rate": 8.760924685320558e-06, "loss": 0.1426, "step": 780 }, { "epoch": 0.7662463627546072, "grad_norm": 0.2495465089144099, "learning_rate": 8.726216452735233e-06, "loss": 0.1427, "step": 790 }, { "epoch": 0.7759456838021338, "grad_norm": 0.16231569101956547, "learning_rate": 8.691099598525222e-06, "loss": 0.1425, "step": 800 }, { "epoch": 0.7856450048496605, "grad_norm": 0.20643117512106057, "learning_rate": 8.655577973649322e-06, "loss": 0.1447, "step": 810 }, { "epoch": 0.7953443258971872, "grad_norm": 0.19353894695637477, "learning_rate": 8.61965547345399e-06, "loss": 0.1431, "step": 820 }, { "epoch": 0.8050436469447139, "grad_norm": 0.1632307697067024, "learning_rate": 8.583336037246187e-06, "loss": 0.1436, "step": 830 }, { "epoch": 0.8147429679922406, "grad_norm": 0.17216990615447947, "learning_rate": 8.54662364786137e-06, "loss": 0.1447, "step": 840 }, { "epoch": 0.8244422890397672, "grad_norm": 0.1651724707314526, "learning_rate": 8.509522331226751e-06, "loss": 0.139, "step": 850 }, { "epoch": 0.8341416100872939, "grad_norm": 0.1568458339839126, "learning_rate": 8.47203615591979e-06, "loss": 0.1427, "step": 860 }, { "epoch": 0.8438409311348206, "grad_norm": 0.17852618591230168, "learning_rate": 8.434169232722043e-06, "loss": 0.1404, "step": 870 }, { "epoch": 0.8535402521823472, "grad_norm": 0.20639355600204873, "learning_rate": 8.395925714168356e-06, "loss": 0.1412, "step": 880 }, { "epoch": 0.8632395732298739, "grad_norm": 0.15073817817287644, "learning_rate": 8.357309794091508e-06, "loss": 0.1413, "step": 890 }, { "epoch": 0.8729388942774006, "grad_norm": 0.15904000752733416, "learning_rate": 8.318325707162293e-06, "loss": 0.1413, "step": 900 }, { "epoch": 0.8826382153249273, "grad_norm": 0.1552685969985047, "learning_rate": 8.278977728425157e-06, "loss": 0.1419, "step": 910 }, { "epoch": 0.8923375363724539, "grad_norm": 0.15706230396222723, "learning_rate": 8.239270172829379e-06, "loss": 0.1416, "step": 920 }, { "epoch": 0.9020368574199806, "grad_norm": 0.17255106752775495, "learning_rate": 8.199207394755892e-06, "loss": 0.1407, "step": 930 }, { "epoch": 0.9117361784675073, "grad_norm": 0.2129566296657695, "learning_rate": 8.158793787539782e-06, "loss": 0.1426, "step": 940 }, { "epoch": 0.9214354995150339, "grad_norm": 0.1520917555155708, "learning_rate": 8.118033782988496e-06, "loss": 0.1425, "step": 950 }, { "epoch": 0.9311348205625606, "grad_norm": 0.14387577079486796, "learning_rate": 8.076931850895858e-06, "loss": 0.1406, "step": 960 }, { "epoch": 0.9408341416100873, "grad_norm": 0.156372446996249, "learning_rate": 8.0354924985519e-06, "loss": 0.1404, "step": 970 }, { "epoch": 0.950533462657614, "grad_norm": 0.13415353564550458, "learning_rate": 7.993720270248583e-06, "loss": 0.1367, "step": 980 }, { "epoch": 0.9602327837051406, "grad_norm": 0.15260385024231266, "learning_rate": 7.951619746781474e-06, "loss": 0.1404, "step": 990 }, { "epoch": 0.9699321047526673, "grad_norm": 0.14296007598794033, "learning_rate": 7.909195544947398e-06, "loss": 0.1379, "step": 1000 }, { "epoch": 0.979631425800194, "grad_norm": 0.1439203772713178, "learning_rate": 7.866452317038164e-06, "loss": 0.1407, "step": 1010 }, { "epoch": 0.9893307468477207, "grad_norm": 0.15601557591631698, "learning_rate": 7.823394750330386e-06, "loss": 0.1378, "step": 1020 }, { "epoch": 0.9990300678952473, "grad_norm": 0.1521155491141262, "learning_rate": 7.780027566571467e-06, "loss": 0.1381, "step": 1030 }, { "epoch": 1.008729388942774, "grad_norm": 0.18883092497874396, "learning_rate": 7.736355521461812e-06, "loss": 0.1289, "step": 1040 }, { "epoch": 1.0184287099903007, "grad_norm": 0.16791508973001082, "learning_rate": 7.692383404133302e-06, "loss": 0.1251, "step": 1050 }, { "epoch": 1.0281280310378274, "grad_norm": 0.1441774496377216, "learning_rate": 7.648116036624125e-06, "loss": 0.1256, "step": 1060 }, { "epoch": 1.037827352085354, "grad_norm": 0.13109750689397975, "learning_rate": 7.6035582733499805e-06, "loss": 0.1255, "step": 1070 }, { "epoch": 1.0475266731328807, "grad_norm": 0.14171432637868595, "learning_rate": 7.5587150005717256e-06, "loss": 0.1241, "step": 1080 }, { "epoch": 1.0572259941804074, "grad_norm": 0.14162368666044384, "learning_rate": 7.5135911358595615e-06, "loss": 0.1273, "step": 1090 }, { "epoch": 1.066925315227934, "grad_norm": 0.13418678548273563, "learning_rate": 7.468191627553752e-06, "loss": 0.1264, "step": 1100 }, { "epoch": 1.0766246362754608, "grad_norm": 0.13196187275552038, "learning_rate": 7.42252145422199e-06, "loss": 0.1293, "step": 1110 }, { "epoch": 1.0863239573229875, "grad_norm": 0.14552608723341326, "learning_rate": 7.376585624113438e-06, "loss": 0.1244, "step": 1120 }, { "epoch": 1.0960232783705142, "grad_norm": 0.14422441886749568, "learning_rate": 7.330389174609516e-06, "loss": 0.1264, "step": 1130 }, { "epoch": 1.1057225994180406, "grad_norm": 0.13834555525544687, "learning_rate": 7.283937171671498e-06, "loss": 0.128, "step": 1140 }, { "epoch": 1.1154219204655673, "grad_norm": 0.13679812310695327, "learning_rate": 7.2372347092849744e-06, "loss": 0.1268, "step": 1150 }, { "epoch": 1.125121241513094, "grad_norm": 0.14580868475877667, "learning_rate": 7.190286908901234e-06, "loss": 0.127, "step": 1160 }, { "epoch": 1.1348205625606207, "grad_norm": 0.14759352493891592, "learning_rate": 7.143098918875643e-06, "loss": 0.1239, "step": 1170 }, { "epoch": 1.1445198836081474, "grad_norm": 0.16306728409304952, "learning_rate": 7.095675913903067e-06, "loss": 0.1252, "step": 1180 }, { "epoch": 1.154219204655674, "grad_norm": 0.13619389268479554, "learning_rate": 7.048023094450412e-06, "loss": 0.1255, "step": 1190 }, { "epoch": 1.1639185257032008, "grad_norm": 0.14865648794317585, "learning_rate": 7.0001456861863236e-06, "loss": 0.125, "step": 1200 }, { "epoch": 1.1736178467507274, "grad_norm": 0.1352158410960604, "learning_rate": 6.952048939408156e-06, "loss": 0.126, "step": 1210 }, { "epoch": 1.1833171677982541, "grad_norm": 0.14931606937805553, "learning_rate": 6.903738128466189e-06, "loss": 0.1244, "step": 1220 }, { "epoch": 1.1930164888457808, "grad_norm": 0.15591971567787935, "learning_rate": 6.8552185511852555e-06, "loss": 0.1257, "step": 1230 }, { "epoch": 1.2027158098933075, "grad_norm": 0.15987884349569545, "learning_rate": 6.806495528283772e-06, "loss": 0.1247, "step": 1240 }, { "epoch": 1.2124151309408342, "grad_norm": 0.173600355468448, "learning_rate": 6.75757440279026e-06, "loss": 0.1266, "step": 1250 }, { "epoch": 1.2221144519883609, "grad_norm": 0.15555585861546212, "learning_rate": 6.708460539457418e-06, "loss": 0.1259, "step": 1260 }, { "epoch": 1.2318137730358876, "grad_norm": 0.13216223386632905, "learning_rate": 6.659159324173823e-06, "loss": 0.1264, "step": 1270 }, { "epoch": 1.2415130940834143, "grad_norm": 0.13732331224860048, "learning_rate": 6.6096761633733065e-06, "loss": 0.1212, "step": 1280 }, { "epoch": 1.251212415130941, "grad_norm": 0.14550514337128806, "learning_rate": 6.5600164834420754e-06, "loss": 0.1232, "step": 1290 }, { "epoch": 1.2609117361784676, "grad_norm": 0.1395324855091477, "learning_rate": 6.510185730123646e-06, "loss": 0.1246, "step": 1300 }, { "epoch": 1.270611057225994, "grad_norm": 0.15143922372224142, "learning_rate": 6.460189367921663e-06, "loss": 0.1222, "step": 1310 }, { "epoch": 1.2803103782735208, "grad_norm": 0.14430877735904407, "learning_rate": 6.410032879500647e-06, "loss": 0.1237, "step": 1320 }, { "epoch": 1.2900096993210475, "grad_norm": 0.15435173824185056, "learning_rate": 6.35972176508477e-06, "loss": 0.1246, "step": 1330 }, { "epoch": 1.2997090203685742, "grad_norm": 0.14283758578201033, "learning_rate": 6.309261541854679e-06, "loss": 0.1246, "step": 1340 }, { "epoch": 1.3094083414161009, "grad_norm": 0.13781861198691472, "learning_rate": 6.258657743342486e-06, "loss": 0.1214, "step": 1350 }, { "epoch": 1.3191076624636275, "grad_norm": 0.13748643897048052, "learning_rate": 6.207915918824952e-06, "loss": 0.1261, "step": 1360 }, { "epoch": 1.3288069835111542, "grad_norm": 0.14790322688240057, "learning_rate": 6.157041632714945e-06, "loss": 0.1255, "step": 1370 }, { "epoch": 1.338506304558681, "grad_norm": 0.13278715076830586, "learning_rate": 6.106040463951237e-06, "loss": 0.1236, "step": 1380 }, { "epoch": 1.3482056256062076, "grad_norm": 0.13946856628394763, "learning_rate": 6.0549180053867114e-06, "loss": 0.1198, "step": 1390 }, { "epoch": 1.3579049466537343, "grad_norm": 0.12852192262109208, "learning_rate": 6.003679863175052e-06, "loss": 0.1241, "step": 1400 }, { "epoch": 1.367604267701261, "grad_norm": 0.14143420891866582, "learning_rate": 5.952331656155951e-06, "loss": 0.1263, "step": 1410 }, { "epoch": 1.3773035887487877, "grad_norm": 0.1282297410386555, "learning_rate": 5.900879015238948e-06, "loss": 0.126, "step": 1420 }, { "epoch": 1.3870029097963141, "grad_norm": 0.13873942443095202, "learning_rate": 5.849327582785943e-06, "loss": 0.1269, "step": 1430 }, { "epoch": 1.3967022308438408, "grad_norm": 0.13656175147704938, "learning_rate": 5.797683011992432e-06, "loss": 0.1203, "step": 1440 }, { "epoch": 1.4064015518913675, "grad_norm": 0.1525890999931462, "learning_rate": 5.745950966267586e-06, "loss": 0.1248, "step": 1450 }, { "epoch": 1.4161008729388942, "grad_norm": 0.1378029168356388, "learning_rate": 5.694137118613185e-06, "loss": 0.1208, "step": 1460 }, { "epoch": 1.4258001939864209, "grad_norm": 0.1349917266146262, "learning_rate": 5.642247151001515e-06, "loss": 0.1219, "step": 1470 }, { "epoch": 1.4354995150339476, "grad_norm": 0.13532958442842166, "learning_rate": 5.590286753752269e-06, "loss": 0.1246, "step": 1480 }, { "epoch": 1.4451988360814743, "grad_norm": 0.13590965633443314, "learning_rate": 5.5382616249085476e-06, "loss": 0.1238, "step": 1490 }, { "epoch": 1.454898157129001, "grad_norm": 0.1302293751307389, "learning_rate": 5.486177469611999e-06, "loss": 0.1218, "step": 1500 }, { "epoch": 1.4645974781765276, "grad_norm": 0.13212636179350218, "learning_rate": 5.434039999477182e-06, "loss": 0.1217, "step": 1510 }, { "epoch": 1.4742967992240543, "grad_norm": 0.15765907573882082, "learning_rate": 5.381854931965238e-06, "loss": 0.1212, "step": 1520 }, { "epoch": 1.483996120271581, "grad_norm": 0.13087502137063067, "learning_rate": 5.32962798975689e-06, "loss": 0.1221, "step": 1530 }, { "epoch": 1.4936954413191077, "grad_norm": 0.1809256405824013, "learning_rate": 5.2773649001248965e-06, "loss": 0.1201, "step": 1540 }, { "epoch": 1.5033947623666344, "grad_norm": 0.12904018631952519, "learning_rate": 5.2250713943059826e-06, "loss": 0.1222, "step": 1550 }, { "epoch": 1.513094083414161, "grad_norm": 0.1293740910081746, "learning_rate": 5.172753206872363e-06, "loss": 0.1209, "step": 1560 }, { "epoch": 1.5227934044616878, "grad_norm": 0.30179091402220243, "learning_rate": 5.120416075102855e-06, "loss": 0.1257, "step": 1570 }, { "epoch": 1.5324927255092144, "grad_norm": 0.1385162792200683, "learning_rate": 5.068065738353748e-06, "loss": 0.124, "step": 1580 }, { "epoch": 1.5421920465567411, "grad_norm": 0.1255449193902108, "learning_rate": 5.015707937429398e-06, "loss": 0.1192, "step": 1590 }, { "epoch": 1.5518913676042678, "grad_norm": 0.15408459889574322, "learning_rate": 4.9633484139526975e-06, "loss": 0.1225, "step": 1600 }, { "epoch": 1.5615906886517945, "grad_norm": 0.13856983999023262, "learning_rate": 4.910992909735432e-06, "loss": 0.1201, "step": 1610 }, { "epoch": 1.5712900096993212, "grad_norm": 0.12207611538378375, "learning_rate": 4.8586471661486345e-06, "loss": 0.1227, "step": 1620 }, { "epoch": 1.5809893307468477, "grad_norm": 0.1266119474511833, "learning_rate": 4.80631692349297e-06, "loss": 0.1232, "step": 1630 }, { "epoch": 1.5906886517943744, "grad_norm": 0.14230780661161255, "learning_rate": 4.754007920369252e-06, "loss": 0.1213, "step": 1640 }, { "epoch": 1.600387972841901, "grad_norm": 0.13743035777356707, "learning_rate": 4.7017258930491474e-06, "loss": 0.1194, "step": 1650 }, { "epoch": 1.6100872938894277, "grad_norm": 0.1386159724833024, "learning_rate": 4.649476574846113e-06, "loss": 0.1206, "step": 1660 }, { "epoch": 1.6197866149369544, "grad_norm": 0.12379147527691, "learning_rate": 4.597265695486685e-06, "loss": 0.122, "step": 1670 }, { "epoch": 1.629485935984481, "grad_norm": 0.13597192298584537, "learning_rate": 4.545098980482151e-06, "loss": 0.1217, "step": 1680 }, { "epoch": 1.6391852570320078, "grad_norm": 0.1281728134758131, "learning_rate": 4.492982150500677e-06, "loss": 0.1222, "step": 1690 }, { "epoch": 1.6488845780795345, "grad_norm": 0.14452895293267878, "learning_rate": 4.44092092073997e-06, "loss": 0.1203, "step": 1700 }, { "epoch": 1.658583899127061, "grad_norm": 0.734748232446473, "learning_rate": 4.388921000300553e-06, "loss": 0.1195, "step": 1710 }, { "epoch": 1.6682832201745876, "grad_norm": 0.13007786192950554, "learning_rate": 4.336988091559688e-06, "loss": 0.1179, "step": 1720 }, { "epoch": 1.6779825412221143, "grad_norm": 0.12183531013572281, "learning_rate": 4.285127889546049e-06, "loss": 0.1214, "step": 1730 }, { "epoch": 1.687681862269641, "grad_norm": 0.13118954244252978, "learning_rate": 4.233346081315197e-06, "loss": 0.1197, "step": 1740 }, { "epoch": 1.6973811833171677, "grad_norm": 0.13481540424732633, "learning_rate": 4.181648345325934e-06, "loss": 0.1173, "step": 1750 }, { "epoch": 1.7070805043646944, "grad_norm": 0.13368272764953815, "learning_rate": 4.13004035081759e-06, "loss": 0.1177, "step": 1760 }, { "epoch": 1.716779825412221, "grad_norm": 0.1405384765881231, "learning_rate": 4.078527757188333e-06, "loss": 0.1193, "step": 1770 }, { "epoch": 1.7264791464597478, "grad_norm": 0.1492903635536138, "learning_rate": 4.02711621337455e-06, "loss": 0.1237, "step": 1780 }, { "epoch": 1.7361784675072744, "grad_norm": 0.13618911961601582, "learning_rate": 3.9758113572313735e-06, "loss": 0.1189, "step": 1790 }, { "epoch": 1.7458777885548011, "grad_norm": 0.12113555025079864, "learning_rate": 3.924618814914435e-06, "loss": 0.119, "step": 1800 }, { "epoch": 1.7555771096023278, "grad_norm": 0.12580610174287832, "learning_rate": 3.873544200262882e-06, "loss": 0.1202, "step": 1810 }, { "epoch": 1.7652764306498545, "grad_norm": 0.12160650948969177, "learning_rate": 3.822593114183777e-06, "loss": 0.1203, "step": 1820 }, { "epoch": 1.7749757516973812, "grad_norm": 0.11538378695593902, "learning_rate": 3.7717711440378695e-06, "loss": 0.1197, "step": 1830 }, { "epoch": 1.7846750727449079, "grad_norm": 0.12474760124557903, "learning_rate": 3.7210838630268986e-06, "loss": 0.1185, "step": 1840 }, { "epoch": 1.7943743937924346, "grad_norm": 0.12741060176067462, "learning_rate": 3.670536829582424e-06, "loss": 0.1191, "step": 1850 }, { "epoch": 1.8040737148399613, "grad_norm": 0.12351598125613471, "learning_rate": 3.6201355867562725e-06, "loss": 0.1191, "step": 1860 }, { "epoch": 1.813773035887488, "grad_norm": 0.14188987252511706, "learning_rate": 3.569885661612691e-06, "loss": 0.1195, "step": 1870 }, { "epoch": 1.8234723569350146, "grad_norm": 0.13634330984512036, "learning_rate": 3.5197925646222387e-06, "loss": 0.1204, "step": 1880 }, { "epoch": 1.8331716779825413, "grad_norm": 0.2373069723174238, "learning_rate": 3.4698617890574972e-06, "loss": 0.1187, "step": 1890 }, { "epoch": 1.842870999030068, "grad_norm": 0.13261383960841805, "learning_rate": 3.4200988103906747e-06, "loss": 0.1181, "step": 1900 }, { "epoch": 1.8525703200775947, "grad_norm": 0.13269073521254607, "learning_rate": 3.3705090856931626e-06, "loss": 0.1189, "step": 1910 }, { "epoch": 1.8622696411251214, "grad_norm": 0.11857183586240762, "learning_rate": 3.3210980530370974e-06, "loss": 0.1163, "step": 1920 }, { "epoch": 1.871968962172648, "grad_norm": 0.12514649915266685, "learning_rate": 3.2718711308990226e-06, "loss": 0.1173, "step": 1930 }, { "epoch": 1.8816682832201745, "grad_norm": 0.13278636126865803, "learning_rate": 3.2228337175656856e-06, "loss": 0.1175, "step": 1940 }, { "epoch": 1.8913676042677012, "grad_norm": 0.1526458979660249, "learning_rate": 3.1739911905420617e-06, "loss": 0.1157, "step": 1950 }, { "epoch": 1.901066925315228, "grad_norm": 0.12356959999521902, "learning_rate": 3.1253489059616448e-06, "loss": 0.1206, "step": 1960 }, { "epoch": 1.9107662463627546, "grad_norm": 0.12931045840893188, "learning_rate": 3.0769121979990845e-06, "loss": 0.1176, "step": 1970 }, { "epoch": 1.9204655674102813, "grad_norm": 0.13043271523994618, "learning_rate": 3.028686378285245e-06, "loss": 0.1188, "step": 1980 }, { "epoch": 1.930164888457808, "grad_norm": 0.1511393413072713, "learning_rate": 2.9806767353247127e-06, "loss": 0.1199, "step": 1990 }, { "epoch": 1.9398642095053347, "grad_norm": 0.1313911423759091, "learning_rate": 2.9328885339158554e-06, "loss": 0.118, "step": 2000 }, { "epoch": 1.9495635305528611, "grad_norm": 0.1264515550648061, "learning_rate": 2.8853270145734846e-06, "loss": 0.1185, "step": 2010 }, { "epoch": 1.9592628516003878, "grad_norm": 0.12231144466512428, "learning_rate": 2.837997392954165e-06, "loss": 0.116, "step": 2020 }, { "epoch": 1.9689621726479145, "grad_norm": 0.14521506304206808, "learning_rate": 2.7909048592842602e-06, "loss": 0.1152, "step": 2030 }, { "epoch": 1.9786614936954412, "grad_norm": 0.126711825889384, "learning_rate": 2.7440545777907747e-06, "loss": 0.1159, "step": 2040 }, { "epoch": 1.9883608147429679, "grad_norm": 0.1681227374854468, "learning_rate": 2.697451686135031e-06, "loss": 0.1186, "step": 2050 }, { "epoch": 1.9980601357904946, "grad_norm": 0.13008493981139174, "learning_rate": 2.6511012948492625e-06, "loss": 0.1172, "step": 2060 }, { "epoch": 2.0077594568380213, "grad_norm": 0.1413967651108439, "learning_rate": 2.6050084867761953e-06, "loss": 0.1045, "step": 2070 }, { "epoch": 2.017458777885548, "grad_norm": 0.1549924427730225, "learning_rate": 2.5591783165116563e-06, "loss": 0.105, "step": 2080 }, { "epoch": 2.0271580989330746, "grad_norm": 0.13493394435352007, "learning_rate": 2.51361580985027e-06, "loss": 0.1038, "step": 2090 }, { "epoch": 2.0368574199806013, "grad_norm": 0.14278275935536047, "learning_rate": 2.4683259632343363e-06, "loss": 0.101, "step": 2100 }, { "epoch": 2.046556741028128, "grad_norm": 0.12912222827072362, "learning_rate": 2.42331374320591e-06, "loss": 0.1023, "step": 2110 }, { "epoch": 2.0562560620756547, "grad_norm": 0.13486110619768377, "learning_rate": 2.3785840858621556e-06, "loss": 0.1038, "step": 2120 }, { "epoch": 2.0659553831231814, "grad_norm": 0.12322475049858893, "learning_rate": 2.334141896314057e-06, "loss": 0.1015, "step": 2130 }, { "epoch": 2.075654704170708, "grad_norm": 0.12313226259292803, "learning_rate": 2.2899920481485192e-06, "loss": 0.1006, "step": 2140 }, { "epoch": 2.0853540252182348, "grad_norm": 0.13084594004574415, "learning_rate": 2.246139382893915e-06, "loss": 0.103, "step": 2150 }, { "epoch": 2.0950533462657615, "grad_norm": 0.11766251876256842, "learning_rate": 2.2025887094891657e-06, "loss": 0.1021, "step": 2160 }, { "epoch": 2.104752667313288, "grad_norm": 0.12060852673739084, "learning_rate": 2.1593448037563795e-06, "loss": 0.1012, "step": 2170 }, { "epoch": 2.114451988360815, "grad_norm": 0.12567405538629176, "learning_rate": 2.116412407877138e-06, "loss": 0.0989, "step": 2180 }, { "epoch": 2.1241513094083415, "grad_norm": 0.1365525172002471, "learning_rate": 2.0737962298724513e-06, "loss": 0.1028, "step": 2190 }, { "epoch": 2.133850630455868, "grad_norm": 0.13749139478988584, "learning_rate": 2.0315009430864762e-06, "loss": 0.0981, "step": 2200 }, { "epoch": 2.143549951503395, "grad_norm": 0.12483408419665704, "learning_rate": 1.989531185674037e-06, "loss": 0.1006, "step": 2210 }, { "epoch": 2.1532492725509216, "grad_norm": 0.12889816969916387, "learning_rate": 1.9478915600919877e-06, "loss": 0.0994, "step": 2220 }, { "epoch": 2.1629485935984483, "grad_norm": 0.13722687929380498, "learning_rate": 1.9065866325945099e-06, "loss": 0.1006, "step": 2230 }, { "epoch": 2.172647914645975, "grad_norm": 0.12731978697579938, "learning_rate": 1.8656209327323704e-06, "loss": 0.1032, "step": 2240 }, { "epoch": 2.1823472356935016, "grad_norm": 0.12992560572466144, "learning_rate": 1.824998952856198e-06, "loss": 0.0995, "step": 2250 }, { "epoch": 2.1920465567410283, "grad_norm": 0.12461701158829513, "learning_rate": 1.784725147623853e-06, "loss": 0.1014, "step": 2260 }, { "epoch": 2.2017458777885546, "grad_norm": 0.12197881380183824, "learning_rate": 1.7448039335119272e-06, "loss": 0.1002, "step": 2270 }, { "epoch": 2.2114451988360813, "grad_norm": 0.12027153954201142, "learning_rate": 1.7052396883314154e-06, "loss": 0.1007, "step": 2280 }, { "epoch": 2.221144519883608, "grad_norm": 0.14042894762171168, "learning_rate": 1.6660367507476539e-06, "loss": 0.1032, "step": 2290 }, { "epoch": 2.2308438409311346, "grad_norm": 0.1304473662542888, "learning_rate": 1.627199419804522e-06, "loss": 0.0974, "step": 2300 }, { "epoch": 2.2405431619786613, "grad_norm": 0.13385797988412498, "learning_rate": 1.5887319544530182e-06, "loss": 0.0993, "step": 2310 }, { "epoch": 2.250242483026188, "grad_norm": 0.12152842920119761, "learning_rate": 1.5506385730842062e-06, "loss": 0.0994, "step": 2320 }, { "epoch": 2.2599418040737147, "grad_norm": 0.15097037450611273, "learning_rate": 1.5129234530666232e-06, "loss": 0.0996, "step": 2330 }, { "epoch": 2.2696411251212414, "grad_norm": 0.13232561112805757, "learning_rate": 1.4755907302881927e-06, "loss": 0.1021, "step": 2340 }, { "epoch": 2.279340446168768, "grad_norm": 0.13689860207073964, "learning_rate": 1.4386444987026705e-06, "loss": 0.1008, "step": 2350 }, { "epoch": 2.2890397672162948, "grad_norm": 0.12697227778436346, "learning_rate": 1.4020888098806924e-06, "loss": 0.1012, "step": 2360 }, { "epoch": 2.2987390882638215, "grad_norm": 0.1306372848154384, "learning_rate": 1.3659276725654863e-06, "loss": 0.0994, "step": 2370 }, { "epoch": 2.308438409311348, "grad_norm": 0.1417516277044696, "learning_rate": 1.3301650522332566e-06, "loss": 0.1021, "step": 2380 }, { "epoch": 2.318137730358875, "grad_norm": 0.12583750650057704, "learning_rate": 1.2948048706583284e-06, "loss": 0.1011, "step": 2390 }, { "epoch": 2.3278370514064015, "grad_norm": 0.12210301430641879, "learning_rate": 1.2598510054830888e-06, "loss": 0.1026, "step": 2400 }, { "epoch": 2.337536372453928, "grad_norm": 0.14086208814152623, "learning_rate": 1.2253072897927437e-06, "loss": 0.1004, "step": 2410 }, { "epoch": 2.347235693501455, "grad_norm": 0.12702340474503365, "learning_rate": 1.1911775116949958e-06, "loss": 0.1026, "step": 2420 }, { "epoch": 2.3569350145489816, "grad_norm": 0.1325904746306228, "learning_rate": 1.1574654139046171e-06, "loss": 0.1004, "step": 2430 }, { "epoch": 2.3666343355965083, "grad_norm": 0.1232419911088865, "learning_rate": 1.1241746933330338e-06, "loss": 0.1021, "step": 2440 }, { "epoch": 2.376333656644035, "grad_norm": 0.11926188716205782, "learning_rate": 1.0913090006829085e-06, "loss": 0.1004, "step": 2450 }, { "epoch": 2.3860329776915616, "grad_norm": 0.1309045847253476, "learning_rate": 1.0588719400478004e-06, "loss": 0.0977, "step": 2460 }, { "epoch": 2.3957322987390883, "grad_norm": 0.13504405075095502, "learning_rate": 1.026867068516943e-06, "loss": 0.1021, "step": 2470 }, { "epoch": 2.405431619786615, "grad_norm": 0.1326298312074988, "learning_rate": 9.952978957851622e-07, "loss": 0.098, "step": 2480 }, { "epoch": 2.4151309408341417, "grad_norm": 0.13381141022665327, "learning_rate": 9.641678837679985e-07, "loss": 0.1, "step": 2490 }, { "epoch": 2.4248302618816684, "grad_norm": 0.12764187585028094, "learning_rate": 9.334804462220748e-07, "loss": 0.0968, "step": 2500 }, { "epoch": 2.434529582929195, "grad_norm": 0.12451918444105284, "learning_rate": 9.032389483707332e-07, "loss": 0.0985, "step": 2510 }, { "epoch": 2.4442289039767218, "grad_norm": 0.1231163492324899, "learning_rate": 8.734467065350022e-07, "loss": 0.1011, "step": 2520 }, { "epoch": 2.4539282250242485, "grad_norm": 0.11884056049855944, "learning_rate": 8.441069877699287e-07, "loss": 0.0988, "step": 2530 }, { "epoch": 2.463627546071775, "grad_norm": 0.12149227620777672, "learning_rate": 8.152230095063051e-07, "loss": 0.1002, "step": 2540 }, { "epoch": 2.473326867119302, "grad_norm": 0.12036233836849276, "learning_rate": 7.867979391978398e-07, "loss": 0.1007, "step": 2550 }, { "epoch": 2.4830261881668285, "grad_norm": 0.12618686097566623, "learning_rate": 7.588348939738116e-07, "loss": 0.0986, "step": 2560 }, { "epoch": 2.492725509214355, "grad_norm": 0.12028662540848738, "learning_rate": 7.31336940297247e-07, "loss": 0.0992, "step": 2570 }, { "epoch": 2.502424830261882, "grad_norm": 0.11545036923542605, "learning_rate": 7.043070936286395e-07, "loss": 0.0978, "step": 2580 }, { "epoch": 2.5121241513094086, "grad_norm": 0.12019777054976608, "learning_rate": 6.777483180952732e-07, "loss": 0.1012, "step": 2590 }, { "epoch": 2.5218234723569353, "grad_norm": 0.11782278703441862, "learning_rate": 6.516635261661775e-07, "loss": 0.0974, "step": 2600 }, { "epoch": 2.531522793404462, "grad_norm": 0.12063704346978395, "learning_rate": 6.260555783327366e-07, "loss": 0.0966, "step": 2610 }, { "epoch": 2.541222114451988, "grad_norm": 0.13985159244922432, "learning_rate": 6.009272827950042e-07, "loss": 0.0999, "step": 2620 }, { "epoch": 2.550921435499515, "grad_norm": 0.1344038669131746, "learning_rate": 5.762813951537582e-07, "loss": 0.101, "step": 2630 }, { "epoch": 2.5606207565470416, "grad_norm": 0.12488293218956574, "learning_rate": 5.521206181083111e-07, "loss": 0.0978, "step": 2640 }, { "epoch": 2.5703200775945683, "grad_norm": 0.12688963896793887, "learning_rate": 5.28447601160132e-07, "loss": 0.0965, "step": 2650 }, { "epoch": 2.580019398642095, "grad_norm": 0.12551768173775268, "learning_rate": 5.052649403223015e-07, "loss": 0.0976, "step": 2660 }, { "epoch": 2.5897187196896216, "grad_norm": 0.11519577314916575, "learning_rate": 4.825751778348259e-07, "loss": 0.0981, "step": 2670 }, { "epoch": 2.5994180407371483, "grad_norm": 0.11984916882145599, "learning_rate": 4.6038080188585135e-07, "loss": 0.0992, "step": 2680 }, { "epoch": 2.609117361784675, "grad_norm": 0.1175248528788484, "learning_rate": 4.38684246338808e-07, "loss": 0.0987, "step": 2690 }, { "epoch": 2.6188166828322017, "grad_norm": 0.13159038738087242, "learning_rate": 4.1748789046551055e-07, "loss": 0.0978, "step": 2700 }, { "epoch": 2.6285160038797284, "grad_norm": 0.12093588925930802, "learning_rate": 3.967940586852409e-07, "loss": 0.0976, "step": 2710 }, { "epoch": 2.638215324927255, "grad_norm": 0.11669957994474343, "learning_rate": 3.7660502030985203e-07, "loss": 0.0988, "step": 2720 }, { "epoch": 2.6479146459747818, "grad_norm": 0.11770882115889388, "learning_rate": 3.569229892949133e-07, "loss": 0.0999, "step": 2730 }, { "epoch": 2.6576139670223085, "grad_norm": 0.11899985694439451, "learning_rate": 3.3775012399692055e-07, "loss": 0.0989, "step": 2740 }, { "epoch": 2.667313288069835, "grad_norm": 0.12610632399439725, "learning_rate": 3.1908852693661116e-07, "loss": 0.0994, "step": 2750 }, { "epoch": 2.677012609117362, "grad_norm": 0.11520791632519826, "learning_rate": 3.0094024456840176e-07, "loss": 0.0987, "step": 2760 }, { "epoch": 2.6867119301648885, "grad_norm": 0.12311171355367961, "learning_rate": 2.833072670559661e-07, "loss": 0.0981, "step": 2770 }, { "epoch": 2.696411251212415, "grad_norm": 0.12430861035520042, "learning_rate": 2.6619152805399286e-07, "loss": 0.098, "step": 2780 }, { "epoch": 2.706110572259942, "grad_norm": 0.1256391775818187, "learning_rate": 2.49594904496141e-07, "loss": 0.0972, "step": 2790 }, { "epoch": 2.7158098933074686, "grad_norm": 0.1132674415609218, "learning_rate": 2.3351921638921193e-07, "loss": 0.0986, "step": 2800 }, { "epoch": 2.7255092143549953, "grad_norm": 0.12235997624262486, "learning_rate": 2.1796622661356238e-07, "loss": 0.1005, "step": 2810 }, { "epoch": 2.735208535402522, "grad_norm": 0.11873323598735666, "learning_rate": 2.0293764072978618e-07, "loss": 0.1017, "step": 2820 }, { "epoch": 2.7449078564500486, "grad_norm": 0.11502932974467346, "learning_rate": 1.8843510679168341e-07, "loss": 0.0969, "step": 2830 }, { "epoch": 2.7546071774975753, "grad_norm": 0.11893095537270826, "learning_rate": 1.744602151655289e-07, "loss": 0.0967, "step": 2840 }, { "epoch": 2.7643064985451016, "grad_norm": 0.11664278880666168, "learning_rate": 1.6101449835567273e-07, "loss": 0.097, "step": 2850 }, { "epoch": 2.7740058195926283, "grad_norm": 0.11762507721842773, "learning_rate": 1.4809943083648194e-07, "loss": 0.0966, "step": 2860 }, { "epoch": 2.783705140640155, "grad_norm": 0.11533591737174845, "learning_rate": 1.3571642889064984e-07, "loss": 0.0965, "step": 2870 }, { "epoch": 2.7934044616876816, "grad_norm": 0.11593673764859609, "learning_rate": 1.2386685045388313e-07, "loss": 0.0934, "step": 2880 }, { "epoch": 2.8031037827352083, "grad_norm": 0.11623880074957675, "learning_rate": 1.1255199496599034e-07, "loss": 0.1002, "step": 2890 }, { "epoch": 2.812803103782735, "grad_norm": 0.11273238019620804, "learning_rate": 1.0177310322838251e-07, "loss": 0.0984, "step": 2900 }, { "epoch": 2.8225024248302617, "grad_norm": 0.11740279413666126, "learning_rate": 9.153135726800599e-08, "loss": 0.0991, "step": 2910 }, { "epoch": 2.8322017458777884, "grad_norm": 0.1279718420944925, "learning_rate": 8.182788020771826e-08, "loss": 0.0995, "step": 2920 }, { "epoch": 2.841901066925315, "grad_norm": 0.1128016665542334, "learning_rate": 7.266373614312927e-08, "loss": 0.0997, "step": 2930 }, { "epoch": 2.8516003879728418, "grad_norm": 0.115197840258161, "learning_rate": 6.403993002590425e-08, "loss": 0.099, "step": 2940 }, { "epoch": 2.8612997090203685, "grad_norm": 0.11734253101361407, "learning_rate": 5.595740755356627e-08, "loss": 0.0961, "step": 2950 }, { "epoch": 2.870999030067895, "grad_norm": 0.11746949240153405, "learning_rate": 4.841705506578587e-08, "loss": 0.0984, "step": 2960 }, { "epoch": 2.880698351115422, "grad_norm": 0.11752266068577234, "learning_rate": 4.1419699447186045e-08, "loss": 0.0995, "step": 2970 }, { "epoch": 2.8903976721629485, "grad_norm": 0.11630585391542382, "learning_rate": 3.4966108036662006e-08, "loss": 0.0987, "step": 2980 }, { "epoch": 2.900096993210475, "grad_norm": 0.12834768725602652, "learning_rate": 2.9056988543239018e-08, "loss": 0.1002, "step": 2990 }, { "epoch": 2.909796314258002, "grad_norm": 0.11104514790150172, "learning_rate": 2.3692988968458398e-08, "loss": 0.0966, "step": 3000 }, { "epoch": 2.9194956353055286, "grad_norm": 0.1262237252529426, "learning_rate": 1.8874697535319897e-08, "loss": 0.0965, "step": 3010 }, { "epoch": 2.9291949563530553, "grad_norm": 0.11707823484874674, "learning_rate": 1.4602642623777752e-08, "loss": 0.0992, "step": 3020 }, { "epoch": 2.938894277400582, "grad_norm": 0.11846337746129845, "learning_rate": 1.0877292712792586e-08, "loss": 0.0954, "step": 3030 }, { "epoch": 2.9485935984481086, "grad_norm": 0.1144938540856074, "learning_rate": 7.699056328964726e-09, "loss": 0.0985, "step": 3040 }, { "epoch": 2.9582929194956353, "grad_norm": 0.1287666028823606, "learning_rate": 5.06828200172893e-09, "loss": 0.1001, "step": 3050 }, { "epoch": 2.967992240543162, "grad_norm": 0.11479880891480539, "learning_rate": 2.9852582251355124e-09, "loss": 0.0979, "step": 3060 }, { "epoch": 2.9776915615906887, "grad_norm": 0.13479592940306032, "learning_rate": 1.4502134262156519e-09, "loss": 0.0973, "step": 3070 }, { "epoch": 2.9873908826382154, "grad_norm": 0.14403422269717034, "learning_rate": 4.6331593993032e-10, "loss": 0.0973, "step": 3080 }, { "epoch": 2.997090203685742, "grad_norm": 0.11557815982586303, "learning_rate": 2.467399070893439e-11, "loss": 0.0964, "step": 3090 }, { "epoch": 3.0, "step": 3093, "total_flos": 3.528412807299072e+16, "train_loss": 0.12713232355097756, "train_runtime": 177593.1778, "train_samples_per_second": 3.064, "train_steps_per_second": 0.017 } ], "logging_steps": 10, "max_steps": 3093, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.528412807299072e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }