{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.984802431610943, "eval_steps": 500, "global_step": 1230, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004052684903748734, "grad_norm": 6.167648898391557, "learning_rate": 3.2520325203252037e-07, "loss": 1.0318, "step": 1 }, { "epoch": 0.008105369807497468, "grad_norm": 6.347812495179655, "learning_rate": 6.504065040650407e-07, "loss": 1.056, "step": 2 }, { "epoch": 0.0121580547112462, "grad_norm": 6.39086695112969, "learning_rate": 9.75609756097561e-07, "loss": 1.0683, "step": 3 }, { "epoch": 0.016210739614994935, "grad_norm": 5.868504359059768, "learning_rate": 1.3008130081300815e-06, "loss": 1.0039, "step": 4 }, { "epoch": 0.020263424518743668, "grad_norm": 5.95258603492728, "learning_rate": 1.6260162601626018e-06, "loss": 1.0091, "step": 5 }, { "epoch": 0.0243161094224924, "grad_norm": 5.686737380141647, "learning_rate": 1.951219512195122e-06, "loss": 1.0146, "step": 6 }, { "epoch": 0.028368794326241134, "grad_norm": 4.845316721839779, "learning_rate": 2.2764227642276426e-06, "loss": 1.0164, "step": 7 }, { "epoch": 0.03242147922998987, "grad_norm": 4.437111552313984, "learning_rate": 2.601626016260163e-06, "loss": 0.9559, "step": 8 }, { "epoch": 0.0364741641337386, "grad_norm": 2.331650380020354, "learning_rate": 2.926829268292683e-06, "loss": 0.9222, "step": 9 }, { "epoch": 0.040526849037487336, "grad_norm": 2.0732459621608426, "learning_rate": 3.2520325203252037e-06, "loss": 0.9407, "step": 10 }, { "epoch": 0.044579533941236066, "grad_norm": 2.0234048735325945, "learning_rate": 3.577235772357724e-06, "loss": 0.9354, "step": 11 }, { "epoch": 0.0486322188449848, "grad_norm": 4.215254282831698, "learning_rate": 3.902439024390244e-06, "loss": 0.9022, "step": 12 }, { "epoch": 0.05268490374873354, "grad_norm": 4.5868341762511715, "learning_rate": 4.227642276422765e-06, "loss": 0.9349, "step": 13 }, { "epoch": 0.05673758865248227, "grad_norm": 4.433058184612854, "learning_rate": 4.552845528455285e-06, "loss": 0.9253, "step": 14 }, { "epoch": 0.060790273556231005, "grad_norm": 4.266424597073819, "learning_rate": 4.8780487804878055e-06, "loss": 0.8974, "step": 15 }, { "epoch": 0.06484295845997974, "grad_norm": 3.1480482357604633, "learning_rate": 5.203252032520326e-06, "loss": 0.8728, "step": 16 }, { "epoch": 0.06889564336372847, "grad_norm": 3.041705383649145, "learning_rate": 5.528455284552846e-06, "loss": 0.8685, "step": 17 }, { "epoch": 0.0729483282674772, "grad_norm": 2.6233469042456554, "learning_rate": 5.853658536585366e-06, "loss": 0.8515, "step": 18 }, { "epoch": 0.07700101317122594, "grad_norm": 2.163027022931509, "learning_rate": 6.178861788617887e-06, "loss": 0.8091, "step": 19 }, { "epoch": 0.08105369807497467, "grad_norm": 1.8410606107564447, "learning_rate": 6.504065040650407e-06, "loss": 0.824, "step": 20 }, { "epoch": 0.0851063829787234, "grad_norm": 1.5676195426530077, "learning_rate": 6.829268292682928e-06, "loss": 0.8095, "step": 21 }, { "epoch": 0.08915906788247213, "grad_norm": 1.6591355070204865, "learning_rate": 7.154471544715448e-06, "loss": 0.8001, "step": 22 }, { "epoch": 0.09321175278622088, "grad_norm": 1.7062461112445475, "learning_rate": 7.4796747967479676e-06, "loss": 0.762, "step": 23 }, { "epoch": 0.0972644376899696, "grad_norm": 1.6812635640813298, "learning_rate": 7.804878048780489e-06, "loss": 0.7807, "step": 24 }, { "epoch": 0.10131712259371833, "grad_norm": 1.1682946514885548, "learning_rate": 8.130081300813009e-06, "loss": 0.7836, "step": 25 }, { "epoch": 0.10536980749746708, "grad_norm": 1.175780955362441, "learning_rate": 8.45528455284553e-06, "loss": 0.7598, "step": 26 }, { "epoch": 0.1094224924012158, "grad_norm": 1.1947293101442185, "learning_rate": 8.78048780487805e-06, "loss": 0.7324, "step": 27 }, { "epoch": 0.11347517730496454, "grad_norm": 1.1439924778893764, "learning_rate": 9.10569105691057e-06, "loss": 0.7708, "step": 28 }, { "epoch": 0.11752786220871327, "grad_norm": 0.8926807480526097, "learning_rate": 9.43089430894309e-06, "loss": 0.7742, "step": 29 }, { "epoch": 0.12158054711246201, "grad_norm": 0.8910934397226351, "learning_rate": 9.756097560975611e-06, "loss": 0.746, "step": 30 }, { "epoch": 0.12563323201621074, "grad_norm": 1.017515700446468, "learning_rate": 1.008130081300813e-05, "loss": 0.7341, "step": 31 }, { "epoch": 0.12968591691995948, "grad_norm": 0.9219012702934337, "learning_rate": 1.0406504065040652e-05, "loss": 0.7175, "step": 32 }, { "epoch": 0.1337386018237082, "grad_norm": 0.7067857437587276, "learning_rate": 1.0731707317073172e-05, "loss": 0.7532, "step": 33 }, { "epoch": 0.13779128672745694, "grad_norm": 0.8234083660446192, "learning_rate": 1.1056910569105692e-05, "loss": 0.7559, "step": 34 }, { "epoch": 0.14184397163120568, "grad_norm": 0.7171954009438662, "learning_rate": 1.1382113821138213e-05, "loss": 0.7137, "step": 35 }, { "epoch": 0.1458966565349544, "grad_norm": 1.8089723082370195, "learning_rate": 1.1707317073170731e-05, "loss": 0.7554, "step": 36 }, { "epoch": 0.14994934143870314, "grad_norm": 0.6242734911079652, "learning_rate": 1.2032520325203254e-05, "loss": 0.7029, "step": 37 }, { "epoch": 0.1540020263424519, "grad_norm": 0.6777927051895012, "learning_rate": 1.2357723577235774e-05, "loss": 0.7363, "step": 38 }, { "epoch": 0.1580547112462006, "grad_norm": 0.642939877950786, "learning_rate": 1.2682926829268294e-05, "loss": 0.7587, "step": 39 }, { "epoch": 0.16210739614994935, "grad_norm": 0.5930362057557689, "learning_rate": 1.3008130081300815e-05, "loss": 0.7029, "step": 40 }, { "epoch": 0.1661600810536981, "grad_norm": 0.6084463235116186, "learning_rate": 1.3333333333333333e-05, "loss": 0.7199, "step": 41 }, { "epoch": 0.1702127659574468, "grad_norm": 0.6053344982178421, "learning_rate": 1.3658536585365855e-05, "loss": 0.7196, "step": 42 }, { "epoch": 0.17426545086119555, "grad_norm": 0.5951326842648802, "learning_rate": 1.3983739837398376e-05, "loss": 0.6796, "step": 43 }, { "epoch": 0.17831813576494426, "grad_norm": 0.5967129397518233, "learning_rate": 1.4308943089430896e-05, "loss": 0.7163, "step": 44 }, { "epoch": 0.182370820668693, "grad_norm": 0.5769137675207878, "learning_rate": 1.4634146341463415e-05, "loss": 0.6974, "step": 45 }, { "epoch": 0.18642350557244175, "grad_norm": 0.5847969054311509, "learning_rate": 1.4959349593495935e-05, "loss": 0.6994, "step": 46 }, { "epoch": 0.19047619047619047, "grad_norm": 0.5888504373368105, "learning_rate": 1.528455284552846e-05, "loss": 0.7094, "step": 47 }, { "epoch": 0.1945288753799392, "grad_norm": 0.6145465354226735, "learning_rate": 1.5609756097560978e-05, "loss": 0.7169, "step": 48 }, { "epoch": 0.19858156028368795, "grad_norm": 0.6394177359489411, "learning_rate": 1.5934959349593496e-05, "loss": 0.681, "step": 49 }, { "epoch": 0.20263424518743667, "grad_norm": 0.6273074421944015, "learning_rate": 1.6260162601626018e-05, "loss": 0.6929, "step": 50 }, { "epoch": 0.2066869300911854, "grad_norm": 0.6349928921016353, "learning_rate": 1.6585365853658537e-05, "loss": 0.6858, "step": 51 }, { "epoch": 0.21073961499493415, "grad_norm": 0.680203067184082, "learning_rate": 1.691056910569106e-05, "loss": 0.6731, "step": 52 }, { "epoch": 0.21479229989868287, "grad_norm": 0.6400603786492668, "learning_rate": 1.7235772357723578e-05, "loss": 0.6882, "step": 53 }, { "epoch": 0.2188449848024316, "grad_norm": 0.7345937234564793, "learning_rate": 1.75609756097561e-05, "loss": 0.6943, "step": 54 }, { "epoch": 0.22289766970618036, "grad_norm": 0.598734191633441, "learning_rate": 1.788617886178862e-05, "loss": 0.6752, "step": 55 }, { "epoch": 0.22695035460992907, "grad_norm": 0.6324661468973752, "learning_rate": 1.821138211382114e-05, "loss": 0.6975, "step": 56 }, { "epoch": 0.23100303951367782, "grad_norm": 0.5859874563149359, "learning_rate": 1.8536585365853663e-05, "loss": 0.6812, "step": 57 }, { "epoch": 0.23505572441742653, "grad_norm": 0.6259138567499695, "learning_rate": 1.886178861788618e-05, "loss": 0.7042, "step": 58 }, { "epoch": 0.23910840932117527, "grad_norm": 0.6111063926683358, "learning_rate": 1.91869918699187e-05, "loss": 0.6817, "step": 59 }, { "epoch": 0.24316109422492402, "grad_norm": 0.7618540826978784, "learning_rate": 1.9512195121951222e-05, "loss": 0.6929, "step": 60 }, { "epoch": 0.24721377912867273, "grad_norm": 0.6426120169369418, "learning_rate": 1.983739837398374e-05, "loss": 0.7019, "step": 61 }, { "epoch": 0.2512664640324215, "grad_norm": 0.719650262344749, "learning_rate": 2.016260162601626e-05, "loss": 0.7096, "step": 62 }, { "epoch": 0.2553191489361702, "grad_norm": 0.5713084777978398, "learning_rate": 2.048780487804878e-05, "loss": 0.706, "step": 63 }, { "epoch": 0.25937183383991896, "grad_norm": 0.7914254335309052, "learning_rate": 2.0813008130081303e-05, "loss": 0.6981, "step": 64 }, { "epoch": 0.2634245187436677, "grad_norm": 0.6243748988190966, "learning_rate": 2.1138211382113822e-05, "loss": 0.6917, "step": 65 }, { "epoch": 0.2674772036474164, "grad_norm": 0.6918979427651847, "learning_rate": 2.1463414634146344e-05, "loss": 0.6954, "step": 66 }, { "epoch": 0.27152988855116517, "grad_norm": 0.6251726885465301, "learning_rate": 2.1788617886178863e-05, "loss": 0.6932, "step": 67 }, { "epoch": 0.2755825734549139, "grad_norm": 0.6289927899059928, "learning_rate": 2.2113821138211385e-05, "loss": 0.6839, "step": 68 }, { "epoch": 0.2796352583586626, "grad_norm": 0.823615779588664, "learning_rate": 2.2439024390243907e-05, "loss": 0.7047, "step": 69 }, { "epoch": 0.28368794326241137, "grad_norm": 0.5798634061506487, "learning_rate": 2.2764227642276426e-05, "loss": 0.6794, "step": 70 }, { "epoch": 0.2877406281661601, "grad_norm": 0.8740507161294093, "learning_rate": 2.3089430894308948e-05, "loss": 0.6917, "step": 71 }, { "epoch": 0.2917933130699088, "grad_norm": 0.6847316537275833, "learning_rate": 2.3414634146341463e-05, "loss": 0.7188, "step": 72 }, { "epoch": 0.29584599797365757, "grad_norm": 0.6717146507509836, "learning_rate": 2.3739837398373985e-05, "loss": 0.7037, "step": 73 }, { "epoch": 0.2998986828774063, "grad_norm": 0.7287082514361286, "learning_rate": 2.4065040650406507e-05, "loss": 0.6878, "step": 74 }, { "epoch": 0.303951367781155, "grad_norm": 0.7402655932944511, "learning_rate": 2.4390243902439026e-05, "loss": 0.6957, "step": 75 }, { "epoch": 0.3080040526849038, "grad_norm": 0.7433179548746084, "learning_rate": 2.4715447154471548e-05, "loss": 0.6985, "step": 76 }, { "epoch": 0.3120567375886525, "grad_norm": 0.6223361686454897, "learning_rate": 2.5040650406504066e-05, "loss": 0.6781, "step": 77 }, { "epoch": 0.3161094224924012, "grad_norm": 0.7141711932588113, "learning_rate": 2.536585365853659e-05, "loss": 0.6629, "step": 78 }, { "epoch": 0.32016210739615, "grad_norm": 0.7514260979136724, "learning_rate": 2.569105691056911e-05, "loss": 0.6631, "step": 79 }, { "epoch": 0.3242147922998987, "grad_norm": 0.932344890017779, "learning_rate": 2.601626016260163e-05, "loss": 0.649, "step": 80 }, { "epoch": 0.3282674772036474, "grad_norm": 0.7445884228457995, "learning_rate": 2.634146341463415e-05, "loss": 0.6814, "step": 81 }, { "epoch": 0.3323201621073962, "grad_norm": 1.033752060115608, "learning_rate": 2.6666666666666667e-05, "loss": 0.6783, "step": 82 }, { "epoch": 0.3363728470111449, "grad_norm": 0.7402027485647631, "learning_rate": 2.699186991869919e-05, "loss": 0.6797, "step": 83 }, { "epoch": 0.3404255319148936, "grad_norm": 0.9693373093096629, "learning_rate": 2.731707317073171e-05, "loss": 0.7093, "step": 84 }, { "epoch": 0.3444782168186423, "grad_norm": 0.8214125176946634, "learning_rate": 2.764227642276423e-05, "loss": 0.6732, "step": 85 }, { "epoch": 0.3485309017223911, "grad_norm": 0.8055834324112491, "learning_rate": 2.796747967479675e-05, "loss": 0.6481, "step": 86 }, { "epoch": 0.3525835866261398, "grad_norm": 0.8709839008437813, "learning_rate": 2.829268292682927e-05, "loss": 0.6934, "step": 87 }, { "epoch": 0.3566362715298885, "grad_norm": 0.7352331686966206, "learning_rate": 2.8617886178861792e-05, "loss": 0.6984, "step": 88 }, { "epoch": 0.3606889564336373, "grad_norm": 0.7988466853595686, "learning_rate": 2.8943089430894314e-05, "loss": 0.6802, "step": 89 }, { "epoch": 0.364741641337386, "grad_norm": 0.7669342573379789, "learning_rate": 2.926829268292683e-05, "loss": 0.6437, "step": 90 }, { "epoch": 0.36879432624113473, "grad_norm": 0.717278327199655, "learning_rate": 2.959349593495935e-05, "loss": 0.6919, "step": 91 }, { "epoch": 0.3728470111448835, "grad_norm": 0.7855973002352786, "learning_rate": 2.991869918699187e-05, "loss": 0.6922, "step": 92 }, { "epoch": 0.3768996960486322, "grad_norm": 0.721690277100239, "learning_rate": 3.0243902439024392e-05, "loss": 0.6875, "step": 93 }, { "epoch": 0.38095238095238093, "grad_norm": 0.7021400060547499, "learning_rate": 3.056910569105692e-05, "loss": 0.6734, "step": 94 }, { "epoch": 0.3850050658561297, "grad_norm": 0.7833322532162378, "learning_rate": 3.089430894308943e-05, "loss": 0.673, "step": 95 }, { "epoch": 0.3890577507598784, "grad_norm": 0.9293861793205748, "learning_rate": 3.1219512195121955e-05, "loss": 0.6742, "step": 96 }, { "epoch": 0.39311043566362713, "grad_norm": 1.0306593508149624, "learning_rate": 3.154471544715447e-05, "loss": 0.6684, "step": 97 }, { "epoch": 0.3971631205673759, "grad_norm": 0.9365742148592389, "learning_rate": 3.186991869918699e-05, "loss": 0.6833, "step": 98 }, { "epoch": 0.4012158054711246, "grad_norm": 0.875421957183987, "learning_rate": 3.2195121951219514e-05, "loss": 0.6903, "step": 99 }, { "epoch": 0.40526849037487334, "grad_norm": 0.8070244209681067, "learning_rate": 3.2520325203252037e-05, "loss": 0.6965, "step": 100 }, { "epoch": 0.4093211752786221, "grad_norm": 1.2072021038272314, "learning_rate": 3.284552845528456e-05, "loss": 0.6604, "step": 101 }, { "epoch": 0.4133738601823708, "grad_norm": 1.0385376009974099, "learning_rate": 3.3170731707317074e-05, "loss": 0.6637, "step": 102 }, { "epoch": 0.41742654508611954, "grad_norm": 1.024204734412347, "learning_rate": 3.3495934959349596e-05, "loss": 0.6886, "step": 103 }, { "epoch": 0.4214792299898683, "grad_norm": 1.0505050096487232, "learning_rate": 3.382113821138212e-05, "loss": 0.6787, "step": 104 }, { "epoch": 0.425531914893617, "grad_norm": 0.9571980865461368, "learning_rate": 3.414634146341463e-05, "loss": 0.6926, "step": 105 }, { "epoch": 0.42958459979736574, "grad_norm": 1.0830581671465136, "learning_rate": 3.4471544715447155e-05, "loss": 0.656, "step": 106 }, { "epoch": 0.4336372847011145, "grad_norm": 0.902566169702378, "learning_rate": 3.479674796747968e-05, "loss": 0.6574, "step": 107 }, { "epoch": 0.4376899696048632, "grad_norm": 0.9224309905110888, "learning_rate": 3.51219512195122e-05, "loss": 0.652, "step": 108 }, { "epoch": 0.44174265450861194, "grad_norm": 0.730238002539342, "learning_rate": 3.544715447154472e-05, "loss": 0.6985, "step": 109 }, { "epoch": 0.4457953394123607, "grad_norm": 0.8368493602637782, "learning_rate": 3.577235772357724e-05, "loss": 0.6627, "step": 110 }, { "epoch": 0.44984802431610943, "grad_norm": 0.7509524426843108, "learning_rate": 3.609756097560976e-05, "loss": 0.6851, "step": 111 }, { "epoch": 0.45390070921985815, "grad_norm": 0.7866920759629977, "learning_rate": 3.642276422764228e-05, "loss": 0.668, "step": 112 }, { "epoch": 0.4579533941236069, "grad_norm": 0.6161650184390867, "learning_rate": 3.67479674796748e-05, "loss": 0.671, "step": 113 }, { "epoch": 0.46200607902735563, "grad_norm": 0.8130424855867256, "learning_rate": 3.7073170731707325e-05, "loss": 0.7099, "step": 114 }, { "epoch": 0.46605876393110435, "grad_norm": 1.2842022052356359, "learning_rate": 3.739837398373984e-05, "loss": 0.6465, "step": 115 }, { "epoch": 0.47011144883485306, "grad_norm": 0.876755312175879, "learning_rate": 3.772357723577236e-05, "loss": 0.6921, "step": 116 }, { "epoch": 0.47416413373860183, "grad_norm": 0.8419998518584061, "learning_rate": 3.804878048780488e-05, "loss": 0.6805, "step": 117 }, { "epoch": 0.47821681864235055, "grad_norm": 0.9599677820203032, "learning_rate": 3.83739837398374e-05, "loss": 0.6978, "step": 118 }, { "epoch": 0.48226950354609927, "grad_norm": 0.811924898172815, "learning_rate": 3.869918699186992e-05, "loss": 0.6739, "step": 119 }, { "epoch": 0.48632218844984804, "grad_norm": 0.7688237600464115, "learning_rate": 3.9024390243902444e-05, "loss": 0.6682, "step": 120 }, { "epoch": 0.49037487335359675, "grad_norm": 0.9730471834233246, "learning_rate": 3.9349593495934966e-05, "loss": 0.6755, "step": 121 }, { "epoch": 0.49442755825734547, "grad_norm": 0.9012683974131351, "learning_rate": 3.967479674796748e-05, "loss": 0.677, "step": 122 }, { "epoch": 0.49848024316109424, "grad_norm": 0.8187007741761511, "learning_rate": 4e-05, "loss": 0.6516, "step": 123 }, { "epoch": 0.502532928064843, "grad_norm": 0.9607905484027193, "learning_rate": 3.999991946137476e-05, "loss": 0.6738, "step": 124 }, { "epoch": 0.5065856129685917, "grad_norm": 0.7829361772146529, "learning_rate": 3.999967784614766e-05, "loss": 0.6568, "step": 125 }, { "epoch": 0.5106382978723404, "grad_norm": 0.5811815909928657, "learning_rate": 3.9999275156264656e-05, "loss": 0.6621, "step": 126 }, { "epoch": 0.5146909827760892, "grad_norm": 0.8020123706445362, "learning_rate": 3.999871139496895e-05, "loss": 0.6638, "step": 127 }, { "epoch": 0.5187436676798379, "grad_norm": 0.8275834768265873, "learning_rate": 3.9997986566800995e-05, "loss": 0.6574, "step": 128 }, { "epoch": 0.5227963525835866, "grad_norm": 0.6936890922275888, "learning_rate": 3.999710067759846e-05, "loss": 0.6796, "step": 129 }, { "epoch": 0.5268490374873354, "grad_norm": 0.6258078657526079, "learning_rate": 3.999605373449617e-05, "loss": 0.6708, "step": 130 }, { "epoch": 0.5309017223910841, "grad_norm": 0.8228076819674753, "learning_rate": 3.9994845745926075e-05, "loss": 0.6981, "step": 131 }, { "epoch": 0.5349544072948328, "grad_norm": 0.9133988210943939, "learning_rate": 3.999347672161713e-05, "loss": 0.6566, "step": 132 }, { "epoch": 0.5390070921985816, "grad_norm": 0.9330195279217748, "learning_rate": 3.999194667259528e-05, "loss": 0.6913, "step": 133 }, { "epoch": 0.5430597771023303, "grad_norm": 0.6280869255027735, "learning_rate": 3.999025561118334e-05, "loss": 0.6616, "step": 134 }, { "epoch": 0.547112462006079, "grad_norm": 0.6921256242749602, "learning_rate": 3.998840355100086e-05, "loss": 0.6735, "step": 135 }, { "epoch": 0.5511651469098278, "grad_norm": 0.8024334357178992, "learning_rate": 3.998639050696409e-05, "loss": 0.6697, "step": 136 }, { "epoch": 0.5552178318135765, "grad_norm": 0.7389507705197214, "learning_rate": 3.998421649528582e-05, "loss": 0.6622, "step": 137 }, { "epoch": 0.5592705167173252, "grad_norm": 0.5777396347394138, "learning_rate": 3.9981881533475234e-05, "loss": 0.6655, "step": 138 }, { "epoch": 0.563323201621074, "grad_norm": 0.7202553964392447, "learning_rate": 3.997938564033779e-05, "loss": 0.6589, "step": 139 }, { "epoch": 0.5673758865248227, "grad_norm": 0.759789149926538, "learning_rate": 3.9976728835975064e-05, "loss": 0.6641, "step": 140 }, { "epoch": 0.5714285714285714, "grad_norm": 0.59814266045635, "learning_rate": 3.9973911141784605e-05, "loss": 0.6854, "step": 141 }, { "epoch": 0.5754812563323202, "grad_norm": 0.5694724611486763, "learning_rate": 3.997093258045973e-05, "loss": 0.6522, "step": 142 }, { "epoch": 0.5795339412360689, "grad_norm": 0.7542096179962985, "learning_rate": 3.996779317598936e-05, "loss": 0.6679, "step": 143 }, { "epoch": 0.5835866261398176, "grad_norm": 0.7869600278819503, "learning_rate": 3.996449295365782e-05, "loss": 0.6554, "step": 144 }, { "epoch": 0.5876393110435664, "grad_norm": 0.5140962741677643, "learning_rate": 3.996103194004467e-05, "loss": 0.6918, "step": 145 }, { "epoch": 0.5916919959473151, "grad_norm": 0.6525220791645695, "learning_rate": 3.995741016302441e-05, "loss": 0.7071, "step": 146 }, { "epoch": 0.5957446808510638, "grad_norm": 0.7237180596476807, "learning_rate": 3.9953627651766364e-05, "loss": 0.674, "step": 147 }, { "epoch": 0.5997973657548126, "grad_norm": 0.688475139492635, "learning_rate": 3.9949684436734325e-05, "loss": 0.6716, "step": 148 }, { "epoch": 0.6038500506585613, "grad_norm": 0.6630390900312946, "learning_rate": 3.994558054968643e-05, "loss": 0.6634, "step": 149 }, { "epoch": 0.60790273556231, "grad_norm": 0.6136144334691922, "learning_rate": 3.994131602367481e-05, "loss": 0.6577, "step": 150 }, { "epoch": 0.6119554204660588, "grad_norm": 0.7659164754226812, "learning_rate": 3.9936890893045376e-05, "loss": 0.6319, "step": 151 }, { "epoch": 0.6160081053698075, "grad_norm": 0.5812014201789653, "learning_rate": 3.993230519343752e-05, "loss": 0.6612, "step": 152 }, { "epoch": 0.6200607902735562, "grad_norm": 0.7309971180003236, "learning_rate": 3.992755896178383e-05, "loss": 0.6586, "step": 153 }, { "epoch": 0.624113475177305, "grad_norm": 0.5813157715882152, "learning_rate": 3.992265223630981e-05, "loss": 0.6562, "step": 154 }, { "epoch": 0.6281661600810537, "grad_norm": 0.6645986427497028, "learning_rate": 3.991758505653355e-05, "loss": 0.6651, "step": 155 }, { "epoch": 0.6322188449848024, "grad_norm": 0.9886091944928685, "learning_rate": 3.991235746326543e-05, "loss": 0.6779, "step": 156 }, { "epoch": 0.6362715298885512, "grad_norm": 0.5782719231928911, "learning_rate": 3.9906969498607745e-05, "loss": 0.6271, "step": 157 }, { "epoch": 0.6403242147923, "grad_norm": 0.7693282918298863, "learning_rate": 3.990142120595444e-05, "loss": 0.6492, "step": 158 }, { "epoch": 0.6443768996960486, "grad_norm": 0.7132802863575435, "learning_rate": 3.98957126299907e-05, "loss": 0.6672, "step": 159 }, { "epoch": 0.6484295845997974, "grad_norm": 0.7580819113254795, "learning_rate": 3.9889843816692596e-05, "loss": 0.6872, "step": 160 }, { "epoch": 0.6524822695035462, "grad_norm": 0.5562842586980432, "learning_rate": 3.9883814813326766e-05, "loss": 0.6267, "step": 161 }, { "epoch": 0.6565349544072948, "grad_norm": 0.6357443704569753, "learning_rate": 3.9877625668449956e-05, "loss": 0.6713, "step": 162 }, { "epoch": 0.6605876393110436, "grad_norm": 0.732784578752325, "learning_rate": 3.98712764319087e-05, "loss": 0.6574, "step": 163 }, { "epoch": 0.6646403242147924, "grad_norm": 0.5777641147619963, "learning_rate": 3.9864767154838864e-05, "loss": 0.634, "step": 164 }, { "epoch": 0.668693009118541, "grad_norm": 0.6591021208964697, "learning_rate": 3.9858097889665277e-05, "loss": 0.6755, "step": 165 }, { "epoch": 0.6727456940222898, "grad_norm": 0.7403664776903102, "learning_rate": 3.985126869010129e-05, "loss": 0.6741, "step": 166 }, { "epoch": 0.6767983789260384, "grad_norm": 0.6828761855823623, "learning_rate": 3.984427961114833e-05, "loss": 0.6484, "step": 167 }, { "epoch": 0.6808510638297872, "grad_norm": 0.6767716831514466, "learning_rate": 3.9837130709095475e-05, "loss": 0.66, "step": 168 }, { "epoch": 0.684903748733536, "grad_norm": 0.626744852782807, "learning_rate": 3.982982204151901e-05, "loss": 0.634, "step": 169 }, { "epoch": 0.6889564336372846, "grad_norm": 0.652846517047525, "learning_rate": 3.982235366728193e-05, "loss": 0.6423, "step": 170 }, { "epoch": 0.6930091185410334, "grad_norm": 0.7599733407242161, "learning_rate": 3.9814725646533505e-05, "loss": 0.6782, "step": 171 }, { "epoch": 0.6970618034447822, "grad_norm": 0.572519115158008, "learning_rate": 3.9806938040708746e-05, "loss": 0.6513, "step": 172 }, { "epoch": 0.7011144883485309, "grad_norm": 0.7641784279124824, "learning_rate": 3.9798990912527976e-05, "loss": 0.6603, "step": 173 }, { "epoch": 0.7051671732522796, "grad_norm": 0.6199226283481147, "learning_rate": 3.979088432599627e-05, "loss": 0.6759, "step": 174 }, { "epoch": 0.7092198581560284, "grad_norm": 0.68191145064256, "learning_rate": 3.9782618346402964e-05, "loss": 0.6924, "step": 175 }, { "epoch": 0.713272543059777, "grad_norm": 0.5629591441061328, "learning_rate": 3.977419304032111e-05, "loss": 0.6372, "step": 176 }, { "epoch": 0.7173252279635258, "grad_norm": 0.6913418774675397, "learning_rate": 3.976560847560697e-05, "loss": 0.6429, "step": 177 }, { "epoch": 0.7213779128672746, "grad_norm": 0.6352205498673283, "learning_rate": 3.9756864721399456e-05, "loss": 0.6447, "step": 178 }, { "epoch": 0.7254305977710233, "grad_norm": 0.6253016658929128, "learning_rate": 3.974796184811956e-05, "loss": 0.6738, "step": 179 }, { "epoch": 0.729483282674772, "grad_norm": 0.7907771004863969, "learning_rate": 3.973889992746979e-05, "loss": 0.6229, "step": 180 }, { "epoch": 0.7335359675785208, "grad_norm": 0.6487811809461457, "learning_rate": 3.972967903243361e-05, "loss": 0.6318, "step": 181 }, { "epoch": 0.7375886524822695, "grad_norm": 0.8125769789219001, "learning_rate": 3.972029923727486e-05, "loss": 0.6888, "step": 182 }, { "epoch": 0.7416413373860182, "grad_norm": 0.9406261631608638, "learning_rate": 3.971076061753709e-05, "loss": 0.6442, "step": 183 }, { "epoch": 0.745694022289767, "grad_norm": 0.6385133768437423, "learning_rate": 3.9701063250043066e-05, "loss": 0.6184, "step": 184 }, { "epoch": 0.7497467071935157, "grad_norm": 0.8931792371984586, "learning_rate": 3.969120721289402e-05, "loss": 0.6594, "step": 185 }, { "epoch": 0.7537993920972644, "grad_norm": 0.6374249608356587, "learning_rate": 3.9681192585469146e-05, "loss": 0.6683, "step": 186 }, { "epoch": 0.7578520770010132, "grad_norm": 0.5965250064122172, "learning_rate": 3.9671019448424865e-05, "loss": 0.6645, "step": 187 }, { "epoch": 0.7619047619047619, "grad_norm": 0.5988671497257495, "learning_rate": 3.966068788369422e-05, "loss": 0.6671, "step": 188 }, { "epoch": 0.7659574468085106, "grad_norm": 0.6278398855657148, "learning_rate": 3.965019797448622e-05, "loss": 0.6551, "step": 189 }, { "epoch": 0.7700101317122594, "grad_norm": 0.579108712206603, "learning_rate": 3.963954980528515e-05, "loss": 0.6608, "step": 190 }, { "epoch": 0.7740628166160081, "grad_norm": 0.5810860711926126, "learning_rate": 3.9628743461849905e-05, "loss": 0.6344, "step": 191 }, { "epoch": 0.7781155015197568, "grad_norm": 0.5422220043872537, "learning_rate": 3.961777903121329e-05, "loss": 0.6099, "step": 192 }, { "epoch": 0.7821681864235056, "grad_norm": 0.7045646802018395, "learning_rate": 3.960665660168131e-05, "loss": 0.6763, "step": 193 }, { "epoch": 0.7862208713272543, "grad_norm": 0.5009113693168984, "learning_rate": 3.9595376262832485e-05, "loss": 0.6299, "step": 194 }, { "epoch": 0.790273556231003, "grad_norm": 0.6627456039777364, "learning_rate": 3.9583938105517127e-05, "loss": 0.6565, "step": 195 }, { "epoch": 0.7943262411347518, "grad_norm": 0.535443329284916, "learning_rate": 3.957234222185657e-05, "loss": 0.6455, "step": 196 }, { "epoch": 0.7983789260385005, "grad_norm": 0.5489568643664365, "learning_rate": 3.9560588705242474e-05, "loss": 0.6735, "step": 197 }, { "epoch": 0.8024316109422492, "grad_norm": 0.7386198918443827, "learning_rate": 3.954867765033605e-05, "loss": 0.698, "step": 198 }, { "epoch": 0.806484295845998, "grad_norm": 0.6584025342575558, "learning_rate": 3.953660915306728e-05, "loss": 0.6545, "step": 199 }, { "epoch": 0.8105369807497467, "grad_norm": 0.4567005415859472, "learning_rate": 3.952438331063419e-05, "loss": 0.6527, "step": 200 }, { "epoch": 0.8145896656534954, "grad_norm": 0.5747667611954319, "learning_rate": 3.951200022150205e-05, "loss": 0.6451, "step": 201 }, { "epoch": 0.8186423505572442, "grad_norm": 0.5442160486071941, "learning_rate": 3.949945998540253e-05, "loss": 0.6732, "step": 202 }, { "epoch": 0.8226950354609929, "grad_norm": 0.5962451177713491, "learning_rate": 3.9486762703332993e-05, "loss": 0.664, "step": 203 }, { "epoch": 0.8267477203647416, "grad_norm": 0.6333555709303281, "learning_rate": 3.947390847755559e-05, "loss": 0.6592, "step": 204 }, { "epoch": 0.8308004052684904, "grad_norm": 0.6356985663463997, "learning_rate": 3.946089741159648e-05, "loss": 0.6553, "step": 205 }, { "epoch": 0.8348530901722391, "grad_norm": 0.6255007415051528, "learning_rate": 3.944772961024501e-05, "loss": 0.6581, "step": 206 }, { "epoch": 0.8389057750759878, "grad_norm": 0.4838339169733258, "learning_rate": 3.943440517955285e-05, "loss": 0.6258, "step": 207 }, { "epoch": 0.8429584599797366, "grad_norm": 0.6183837063519475, "learning_rate": 3.9420924226833126e-05, "loss": 0.649, "step": 208 }, { "epoch": 0.8470111448834853, "grad_norm": 0.5468220534611677, "learning_rate": 3.9407286860659566e-05, "loss": 0.6504, "step": 209 }, { "epoch": 0.851063829787234, "grad_norm": 0.5198056729443817, "learning_rate": 3.9393493190865657e-05, "loss": 0.661, "step": 210 }, { "epoch": 0.8551165146909828, "grad_norm": 0.49124252014846126, "learning_rate": 3.937954332854371e-05, "loss": 0.6085, "step": 211 }, { "epoch": 0.8591691995947315, "grad_norm": 0.5364391818451996, "learning_rate": 3.9365437386044016e-05, "loss": 0.6365, "step": 212 }, { "epoch": 0.8632218844984803, "grad_norm": 0.6006284773855927, "learning_rate": 3.935117547697387e-05, "loss": 0.63, "step": 213 }, { "epoch": 0.867274569402229, "grad_norm": 0.48364489641596037, "learning_rate": 3.933675771619675e-05, "loss": 0.6386, "step": 214 }, { "epoch": 0.8713272543059777, "grad_norm": 0.679659719677668, "learning_rate": 3.932218421983131e-05, "loss": 0.6222, "step": 215 }, { "epoch": 0.8753799392097265, "grad_norm": 0.5376577238661026, "learning_rate": 3.9307455105250484e-05, "loss": 0.642, "step": 216 }, { "epoch": 0.8794326241134752, "grad_norm": 0.6546326026688126, "learning_rate": 3.929257049108054e-05, "loss": 0.6743, "step": 217 }, { "epoch": 0.8834853090172239, "grad_norm": 0.6525453163129142, "learning_rate": 3.927753049720011e-05, "loss": 0.6793, "step": 218 }, { "epoch": 0.8875379939209727, "grad_norm": 0.5843734165520835, "learning_rate": 3.9262335244739234e-05, "loss": 0.6465, "step": 219 }, { "epoch": 0.8915906788247214, "grad_norm": 0.5198437560394561, "learning_rate": 3.92469848560784e-05, "loss": 0.6622, "step": 220 }, { "epoch": 0.8956433637284701, "grad_norm": 0.5277570367845225, "learning_rate": 3.923147945484751e-05, "loss": 0.6248, "step": 221 }, { "epoch": 0.8996960486322189, "grad_norm": 0.5324262859558979, "learning_rate": 3.9215819165924956e-05, "loss": 0.6573, "step": 222 }, { "epoch": 0.9037487335359676, "grad_norm": 0.6356450491120629, "learning_rate": 3.920000411543654e-05, "loss": 0.6655, "step": 223 }, { "epoch": 0.9078014184397163, "grad_norm": 0.5020304511715131, "learning_rate": 3.9184034430754495e-05, "loss": 0.6518, "step": 224 }, { "epoch": 0.9118541033434651, "grad_norm": 0.6761218155366049, "learning_rate": 3.916791024049648e-05, "loss": 0.6419, "step": 225 }, { "epoch": 0.9159067882472138, "grad_norm": 0.5477798583367588, "learning_rate": 3.91516316745245e-05, "loss": 0.6521, "step": 226 }, { "epoch": 0.9199594731509625, "grad_norm": 0.5235486652857558, "learning_rate": 3.913519886394389e-05, "loss": 0.654, "step": 227 }, { "epoch": 0.9240121580547113, "grad_norm": 0.5318085733561676, "learning_rate": 3.911861194110225e-05, "loss": 0.602, "step": 228 }, { "epoch": 0.92806484295846, "grad_norm": 0.47327149859685425, "learning_rate": 3.910187103958837e-05, "loss": 0.6208, "step": 229 }, { "epoch": 0.9321175278622087, "grad_norm": 0.5774412798693223, "learning_rate": 3.908497629423117e-05, "loss": 0.6927, "step": 230 }, { "epoch": 0.9361702127659575, "grad_norm": 0.5012351161324542, "learning_rate": 3.9067927841098614e-05, "loss": 0.6608, "step": 231 }, { "epoch": 0.9402228976697061, "grad_norm": 0.5654080613042578, "learning_rate": 3.9050725817496594e-05, "loss": 0.6413, "step": 232 }, { "epoch": 0.9442755825734549, "grad_norm": 0.5756049621432757, "learning_rate": 3.9033370361967844e-05, "loss": 0.6329, "step": 233 }, { "epoch": 0.9483282674772037, "grad_norm": 0.5301552288404705, "learning_rate": 3.901586161429081e-05, "loss": 0.6551, "step": 234 }, { "epoch": 0.9523809523809523, "grad_norm": 0.48164756413613646, "learning_rate": 3.8998199715478545e-05, "loss": 0.6377, "step": 235 }, { "epoch": 0.9564336372847011, "grad_norm": 0.5042103283518745, "learning_rate": 3.8980384807777564e-05, "loss": 0.6416, "step": 236 }, { "epoch": 0.9604863221884499, "grad_norm": 0.5240695797874856, "learning_rate": 3.896241703466667e-05, "loss": 0.6454, "step": 237 }, { "epoch": 0.9645390070921985, "grad_norm": 0.480102592406313, "learning_rate": 3.894429654085585e-05, "loss": 0.6156, "step": 238 }, { "epoch": 0.9685916919959473, "grad_norm": 0.5392021228543473, "learning_rate": 3.892602347228505e-05, "loss": 0.6688, "step": 239 }, { "epoch": 0.9726443768996961, "grad_norm": 0.4558541562487634, "learning_rate": 3.890759797612307e-05, "loss": 0.6392, "step": 240 }, { "epoch": 0.9766970618034447, "grad_norm": 0.5509554561610756, "learning_rate": 3.888902020076632e-05, "loss": 0.6368, "step": 241 }, { "epoch": 0.9807497467071935, "grad_norm": 0.4902576886131729, "learning_rate": 3.887029029583764e-05, "loss": 0.6532, "step": 242 }, { "epoch": 0.9848024316109423, "grad_norm": 0.4350141761025598, "learning_rate": 3.8851408412185125e-05, "loss": 0.6073, "step": 243 }, { "epoch": 0.9888551165146909, "grad_norm": 0.44954792033729896, "learning_rate": 3.8832374701880855e-05, "loss": 0.6045, "step": 244 }, { "epoch": 0.9929078014184397, "grad_norm": 0.5310462875194559, "learning_rate": 3.881318931821972e-05, "loss": 0.6242, "step": 245 }, { "epoch": 0.9969604863221885, "grad_norm": 0.5195162896695701, "learning_rate": 3.879385241571817e-05, "loss": 0.6352, "step": 246 }, { "epoch": 1.0010131712259371, "grad_norm": 0.46539903847427483, "learning_rate": 3.8774364150112955e-05, "loss": 0.5993, "step": 247 }, { "epoch": 1.005065856129686, "grad_norm": 0.5721331146510316, "learning_rate": 3.8754724678359884e-05, "loss": 0.5266, "step": 248 }, { "epoch": 1.0091185410334347, "grad_norm": 0.4630175386937948, "learning_rate": 3.873493415863256e-05, "loss": 0.5135, "step": 249 }, { "epoch": 1.0131712259371835, "grad_norm": 0.5971421598448525, "learning_rate": 3.871499275032111e-05, "loss": 0.5353, "step": 250 }, { "epoch": 1.0172239108409322, "grad_norm": 0.5971328548121767, "learning_rate": 3.869490061403091e-05, "loss": 0.5355, "step": 251 }, { "epoch": 1.0212765957446808, "grad_norm": 0.5567927419301527, "learning_rate": 3.867465791158124e-05, "loss": 0.5244, "step": 252 }, { "epoch": 1.0253292806484295, "grad_norm": 0.5883646614816578, "learning_rate": 3.865426480600407e-05, "loss": 0.5235, "step": 253 }, { "epoch": 1.0293819655521783, "grad_norm": 0.5419714506776818, "learning_rate": 3.863372146154264e-05, "loss": 0.5216, "step": 254 }, { "epoch": 1.033434650455927, "grad_norm": 0.6058246665482957, "learning_rate": 3.861302804365024e-05, "loss": 0.524, "step": 255 }, { "epoch": 1.0374873353596759, "grad_norm": 0.5870085341115271, "learning_rate": 3.85921847189888e-05, "loss": 0.5501, "step": 256 }, { "epoch": 1.0415400202634246, "grad_norm": 0.540951531119635, "learning_rate": 3.85711916554276e-05, "loss": 0.4946, "step": 257 }, { "epoch": 1.0455927051671732, "grad_norm": 0.7588521014997948, "learning_rate": 3.85500490220419e-05, "loss": 0.5275, "step": 258 }, { "epoch": 1.049645390070922, "grad_norm": 0.5872215773115123, "learning_rate": 3.852875698911154e-05, "loss": 0.5137, "step": 259 }, { "epoch": 1.0536980749746707, "grad_norm": 0.813939027396721, "learning_rate": 3.850731572811963e-05, "loss": 0.4953, "step": 260 }, { "epoch": 1.0577507598784195, "grad_norm": 0.7157498655664356, "learning_rate": 3.848572541175116e-05, "loss": 0.5209, "step": 261 }, { "epoch": 1.0618034447821683, "grad_norm": 0.5142387405382273, "learning_rate": 3.846398621389154e-05, "loss": 0.5314, "step": 262 }, { "epoch": 1.0658561296859168, "grad_norm": 0.6085930865447006, "learning_rate": 3.84420983096253e-05, "loss": 0.5222, "step": 263 }, { "epoch": 1.0699088145896656, "grad_norm": 0.536939258154577, "learning_rate": 3.8420061875234606e-05, "loss": 0.5426, "step": 264 }, { "epoch": 1.0739614994934144, "grad_norm": 0.5035325296842744, "learning_rate": 3.839787708819787e-05, "loss": 0.5438, "step": 265 }, { "epoch": 1.0780141843971631, "grad_norm": 0.5696625542686482, "learning_rate": 3.8375544127188325e-05, "loss": 0.5245, "step": 266 }, { "epoch": 1.082066869300912, "grad_norm": 0.5099520099300787, "learning_rate": 3.8353063172072564e-05, "loss": 0.5198, "step": 267 }, { "epoch": 1.0861195542046607, "grad_norm": 0.514341466102075, "learning_rate": 3.8330434403909105e-05, "loss": 0.5285, "step": 268 }, { "epoch": 1.0901722391084094, "grad_norm": 0.5269907753925314, "learning_rate": 3.8307658004946934e-05, "loss": 0.5109, "step": 269 }, { "epoch": 1.094224924012158, "grad_norm": 0.48924322825629246, "learning_rate": 3.8284734158624046e-05, "loss": 0.522, "step": 270 }, { "epoch": 1.0982776089159068, "grad_norm": 0.5538876706026832, "learning_rate": 3.826166304956594e-05, "loss": 0.5051, "step": 271 }, { "epoch": 1.1023302938196555, "grad_norm": 0.5794742459368873, "learning_rate": 3.8238444863584164e-05, "loss": 0.5242, "step": 272 }, { "epoch": 1.1063829787234043, "grad_norm": 0.4717872228709027, "learning_rate": 3.821507978767479e-05, "loss": 0.5191, "step": 273 }, { "epoch": 1.110435663627153, "grad_norm": 0.550044522384166, "learning_rate": 3.819156801001693e-05, "loss": 0.5358, "step": 274 }, { "epoch": 1.1144883485309016, "grad_norm": 0.5072038334648188, "learning_rate": 3.816790971997121e-05, "loss": 0.5351, "step": 275 }, { "epoch": 1.1185410334346504, "grad_norm": 0.5807660279909721, "learning_rate": 3.8144105108078246e-05, "loss": 0.5459, "step": 276 }, { "epoch": 1.1225937183383992, "grad_norm": 0.533811678308289, "learning_rate": 3.81201543660571e-05, "loss": 0.5217, "step": 277 }, { "epoch": 1.126646403242148, "grad_norm": 0.7354620768312641, "learning_rate": 3.809605768680377e-05, "loss": 0.5195, "step": 278 }, { "epoch": 1.1306990881458967, "grad_norm": 0.5129443102369141, "learning_rate": 3.807181526438958e-05, "loss": 0.531, "step": 279 }, { "epoch": 1.1347517730496455, "grad_norm": 0.7242399335538623, "learning_rate": 3.8047427294059697e-05, "loss": 0.5057, "step": 280 }, { "epoch": 1.1388044579533942, "grad_norm": 0.6088801848681012, "learning_rate": 3.802289397223145e-05, "loss": 0.5408, "step": 281 }, { "epoch": 1.1428571428571428, "grad_norm": 0.5106813240324434, "learning_rate": 3.7998215496492854e-05, "loss": 0.5276, "step": 282 }, { "epoch": 1.1469098277608916, "grad_norm": 0.6671448117350898, "learning_rate": 3.797339206560096e-05, "loss": 0.5296, "step": 283 }, { "epoch": 1.1509625126646403, "grad_norm": 0.5222406639445356, "learning_rate": 3.794842387948027e-05, "loss": 0.5185, "step": 284 }, { "epoch": 1.155015197568389, "grad_norm": 0.6044830847551335, "learning_rate": 3.7923311139221114e-05, "loss": 0.5165, "step": 285 }, { "epoch": 1.1590678824721379, "grad_norm": 0.5582160585593303, "learning_rate": 3.7898054047078054e-05, "loss": 0.5223, "step": 286 }, { "epoch": 1.1631205673758864, "grad_norm": 0.5517860414043275, "learning_rate": 3.787265280646825e-05, "loss": 0.5182, "step": 287 }, { "epoch": 1.1671732522796352, "grad_norm": 0.5296304576687654, "learning_rate": 3.7847107621969786e-05, "loss": 0.5124, "step": 288 }, { "epoch": 1.171225937183384, "grad_norm": 0.5107525372836029, "learning_rate": 3.7821418699320064e-05, "loss": 0.5165, "step": 289 }, { "epoch": 1.1752786220871327, "grad_norm": 0.6064099923099067, "learning_rate": 3.7795586245414145e-05, "loss": 0.5364, "step": 290 }, { "epoch": 1.1793313069908815, "grad_norm": 0.5327554103630293, "learning_rate": 3.776961046830306e-05, "loss": 0.5463, "step": 291 }, { "epoch": 1.1833839918946303, "grad_norm": 0.5189107655892751, "learning_rate": 3.774349157719215e-05, "loss": 0.515, "step": 292 }, { "epoch": 1.1874366767983788, "grad_norm": 0.5312590699745653, "learning_rate": 3.7717229782439365e-05, "loss": 0.5314, "step": 293 }, { "epoch": 1.1914893617021276, "grad_norm": 0.5371671359053948, "learning_rate": 3.769082529555359e-05, "loss": 0.5125, "step": 294 }, { "epoch": 1.1955420466058764, "grad_norm": 0.5368223525309944, "learning_rate": 3.766427832919294e-05, "loss": 0.5386, "step": 295 }, { "epoch": 1.1995947315096251, "grad_norm": 0.5362709443242086, "learning_rate": 3.7637589097163024e-05, "loss": 0.5292, "step": 296 }, { "epoch": 1.203647416413374, "grad_norm": 0.4905563442824916, "learning_rate": 3.761075781441526e-05, "loss": 0.4917, "step": 297 }, { "epoch": 1.2077001013171227, "grad_norm": 0.5403762197429501, "learning_rate": 3.75837846970451e-05, "loss": 0.5299, "step": 298 }, { "epoch": 1.2117527862208712, "grad_norm": 0.578030864935955, "learning_rate": 3.755666996229032e-05, "loss": 0.5171, "step": 299 }, { "epoch": 1.21580547112462, "grad_norm": 0.43797358524235913, "learning_rate": 3.752941382852927e-05, "loss": 0.5165, "step": 300 }, { "epoch": 1.2198581560283688, "grad_norm": 0.4421969448614822, "learning_rate": 3.7502016515279115e-05, "loss": 0.513, "step": 301 }, { "epoch": 1.2239108409321175, "grad_norm": 0.47690204193648944, "learning_rate": 3.7474478243194043e-05, "loss": 0.5308, "step": 302 }, { "epoch": 1.2279635258358663, "grad_norm": 0.5284829827970645, "learning_rate": 3.744679923406351e-05, "loss": 0.553, "step": 303 }, { "epoch": 1.232016210739615, "grad_norm": 0.48415755978944, "learning_rate": 3.741897971081043e-05, "loss": 0.5036, "step": 304 }, { "epoch": 1.2360688956433636, "grad_norm": 0.5140823736996428, "learning_rate": 3.739101989748946e-05, "loss": 0.5157, "step": 305 }, { "epoch": 1.2401215805471124, "grad_norm": 0.4469363340877741, "learning_rate": 3.7362920019285066e-05, "loss": 0.536, "step": 306 }, { "epoch": 1.2441742654508612, "grad_norm": 0.5903783771695209, "learning_rate": 3.73346803025098e-05, "loss": 0.5134, "step": 307 }, { "epoch": 1.24822695035461, "grad_norm": 0.5098387526445031, "learning_rate": 3.730630097460247e-05, "loss": 0.5365, "step": 308 }, { "epoch": 1.2522796352583587, "grad_norm": 0.5414186717082425, "learning_rate": 3.727778226412628e-05, "loss": 0.532, "step": 309 }, { "epoch": 1.2563323201621075, "grad_norm": 0.6857138230336729, "learning_rate": 3.7249124400767006e-05, "loss": 0.5418, "step": 310 }, { "epoch": 1.260385005065856, "grad_norm": 0.48861001889199024, "learning_rate": 3.722032761533114e-05, "loss": 0.5304, "step": 311 }, { "epoch": 1.2644376899696048, "grad_norm": 0.5676474000363062, "learning_rate": 3.719139213974403e-05, "loss": 0.5389, "step": 312 }, { "epoch": 1.2684903748733536, "grad_norm": 0.5812308154357729, "learning_rate": 3.7162318207048006e-05, "loss": 0.5244, "step": 313 }, { "epoch": 1.2725430597771024, "grad_norm": 0.5203803151565424, "learning_rate": 3.713310605140055e-05, "loss": 0.5368, "step": 314 }, { "epoch": 1.2765957446808511, "grad_norm": 0.5841171386128461, "learning_rate": 3.710375590807233e-05, "loss": 0.5267, "step": 315 }, { "epoch": 1.2806484295845997, "grad_norm": 0.6451730438846078, "learning_rate": 3.7074268013445365e-05, "loss": 0.55, "step": 316 }, { "epoch": 1.2847011144883485, "grad_norm": 0.6067873745741551, "learning_rate": 3.7044642605011114e-05, "loss": 0.5299, "step": 317 }, { "epoch": 1.2887537993920972, "grad_norm": 0.5034572434610671, "learning_rate": 3.701487992136854e-05, "loss": 0.5226, "step": 318 }, { "epoch": 1.292806484295846, "grad_norm": 0.6086857533591217, "learning_rate": 3.69849802022222e-05, "loss": 0.5217, "step": 319 }, { "epoch": 1.2968591691995948, "grad_norm": 0.5837386215558551, "learning_rate": 3.6954943688380334e-05, "loss": 0.5394, "step": 320 }, { "epoch": 1.3009118541033435, "grad_norm": 0.6215797401214238, "learning_rate": 3.692477062175289e-05, "loss": 0.5226, "step": 321 }, { "epoch": 1.3049645390070923, "grad_norm": 0.5173019410083438, "learning_rate": 3.689446124534958e-05, "loss": 0.4966, "step": 322 }, { "epoch": 1.3090172239108409, "grad_norm": 0.6245045719766499, "learning_rate": 3.686401580327799e-05, "loss": 0.5448, "step": 323 }, { "epoch": 1.3130699088145896, "grad_norm": 0.5193931548337708, "learning_rate": 3.683343454074149e-05, "loss": 0.514, "step": 324 }, { "epoch": 1.3171225937183384, "grad_norm": 0.49935165424524225, "learning_rate": 3.6802717704037386e-05, "loss": 0.5333, "step": 325 }, { "epoch": 1.3211752786220872, "grad_norm": 0.4949988245199749, "learning_rate": 3.6771865540554855e-05, "loss": 0.4995, "step": 326 }, { "epoch": 1.325227963525836, "grad_norm": 0.5411766741565728, "learning_rate": 3.674087829877297e-05, "loss": 0.5352, "step": 327 }, { "epoch": 1.3292806484295845, "grad_norm": 0.5166613605613284, "learning_rate": 3.6709756228258735e-05, "loss": 0.5243, "step": 328 }, { "epoch": 1.3333333333333333, "grad_norm": 0.5065243071725839, "learning_rate": 3.667849957966501e-05, "loss": 0.5159, "step": 329 }, { "epoch": 1.337386018237082, "grad_norm": 0.4874077618925925, "learning_rate": 3.6647108604728546e-05, "loss": 0.5253, "step": 330 }, { "epoch": 1.3414387031408308, "grad_norm": 0.5981950851498741, "learning_rate": 3.661558355626795e-05, "loss": 0.5678, "step": 331 }, { "epoch": 1.3454913880445796, "grad_norm": 0.5463181943305964, "learning_rate": 3.658392468818163e-05, "loss": 0.5304, "step": 332 }, { "epoch": 1.3495440729483283, "grad_norm": 0.48947544639011564, "learning_rate": 3.655213225544574e-05, "loss": 0.5455, "step": 333 }, { "epoch": 1.3535967578520771, "grad_norm": 0.5467682704034038, "learning_rate": 3.652020651411218e-05, "loss": 0.533, "step": 334 }, { "epoch": 1.3576494427558257, "grad_norm": 0.4687856411038806, "learning_rate": 3.6488147721306474e-05, "loss": 0.5278, "step": 335 }, { "epoch": 1.3617021276595744, "grad_norm": 0.4601428281212315, "learning_rate": 3.645595613522574e-05, "loss": 0.5205, "step": 336 }, { "epoch": 1.3657548125633232, "grad_norm": 0.47993191500684906, "learning_rate": 3.642363201513657e-05, "loss": 0.5049, "step": 337 }, { "epoch": 1.369807497467072, "grad_norm": 0.49662918808162565, "learning_rate": 3.6391175621373006e-05, "loss": 0.5077, "step": 338 }, { "epoch": 1.3738601823708207, "grad_norm": 0.4978664008115118, "learning_rate": 3.6358587215334355e-05, "loss": 0.5336, "step": 339 }, { "epoch": 1.3779128672745693, "grad_norm": 0.5490575611293455, "learning_rate": 3.632586705948318e-05, "loss": 0.537, "step": 340 }, { "epoch": 1.381965552178318, "grad_norm": 0.44963038464161614, "learning_rate": 3.629301541734311e-05, "loss": 0.5261, "step": 341 }, { "epoch": 1.3860182370820668, "grad_norm": 0.5026458300272734, "learning_rate": 3.626003255349676e-05, "loss": 0.5196, "step": 342 }, { "epoch": 1.3900709219858156, "grad_norm": 0.43240902926095, "learning_rate": 3.622691873358357e-05, "loss": 0.5067, "step": 343 }, { "epoch": 1.3941236068895644, "grad_norm": 0.5315792537266139, "learning_rate": 3.61936742242977e-05, "loss": 0.5456, "step": 344 }, { "epoch": 1.3981762917933132, "grad_norm": 0.5614850785234248, "learning_rate": 3.6160299293385864e-05, "loss": 0.5318, "step": 345 }, { "epoch": 1.402228976697062, "grad_norm": 0.4707818666771937, "learning_rate": 3.612679420964516e-05, "loss": 0.5028, "step": 346 }, { "epoch": 1.4062816616008105, "grad_norm": 0.5368451166894669, "learning_rate": 3.609315924292092e-05, "loss": 0.5231, "step": 347 }, { "epoch": 1.4103343465045592, "grad_norm": 0.48375150574836834, "learning_rate": 3.6059394664104554e-05, "loss": 0.5362, "step": 348 }, { "epoch": 1.414387031408308, "grad_norm": 0.5675650103542361, "learning_rate": 3.602550074513133e-05, "loss": 0.5209, "step": 349 }, { "epoch": 1.4184397163120568, "grad_norm": 0.5219281047486538, "learning_rate": 3.599147775897822e-05, "loss": 0.5318, "step": 350 }, { "epoch": 1.4224924012158056, "grad_norm": 0.5329028869460057, "learning_rate": 3.595732597966167e-05, "loss": 0.5333, "step": 351 }, { "epoch": 1.426545086119554, "grad_norm": 0.4672111394685723, "learning_rate": 3.592304568223542e-05, "loss": 0.5363, "step": 352 }, { "epoch": 1.4305977710233029, "grad_norm": 0.4945061168429465, "learning_rate": 3.588863714278826e-05, "loss": 0.5335, "step": 353 }, { "epoch": 1.4346504559270516, "grad_norm": 0.48559926565972317, "learning_rate": 3.585410063844186e-05, "loss": 0.5181, "step": 354 }, { "epoch": 1.4387031408308004, "grad_norm": 0.4652278494777882, "learning_rate": 3.581943644734846e-05, "loss": 0.527, "step": 355 }, { "epoch": 1.4427558257345492, "grad_norm": 0.483349917112747, "learning_rate": 3.578464484868869e-05, "loss": 0.5162, "step": 356 }, { "epoch": 1.4468085106382977, "grad_norm": 0.4962336407265618, "learning_rate": 3.5749726122669316e-05, "loss": 0.5305, "step": 357 }, { "epoch": 1.4508611955420467, "grad_norm": 0.47819057209537086, "learning_rate": 3.5714680550520943e-05, "loss": 0.5376, "step": 358 }, { "epoch": 1.4549138804457953, "grad_norm": 0.5473935166195258, "learning_rate": 3.5679508414495794e-05, "loss": 0.5229, "step": 359 }, { "epoch": 1.458966565349544, "grad_norm": 0.5224230271081634, "learning_rate": 3.564420999786543e-05, "loss": 0.5317, "step": 360 }, { "epoch": 1.4630192502532928, "grad_norm": 0.4834531061601308, "learning_rate": 3.560878558491842e-05, "loss": 0.5281, "step": 361 }, { "epoch": 1.4670719351570416, "grad_norm": 0.49977576562007026, "learning_rate": 3.5573235460958145e-05, "loss": 0.5458, "step": 362 }, { "epoch": 1.4711246200607904, "grad_norm": 0.518900685921013, "learning_rate": 3.553755991230039e-05, "loss": 0.5327, "step": 363 }, { "epoch": 1.475177304964539, "grad_norm": 0.5056168019028707, "learning_rate": 3.5501759226271144e-05, "loss": 0.5349, "step": 364 }, { "epoch": 1.4792299898682877, "grad_norm": 0.5155909978528884, "learning_rate": 3.546583369120419e-05, "loss": 0.527, "step": 365 }, { "epoch": 1.4832826747720365, "grad_norm": 0.4793050247055886, "learning_rate": 3.5429783596438864e-05, "loss": 0.5175, "step": 366 }, { "epoch": 1.4873353596757852, "grad_norm": 0.4868088680443328, "learning_rate": 3.539360923231766e-05, "loss": 0.5274, "step": 367 }, { "epoch": 1.491388044579534, "grad_norm": 0.5482405051288772, "learning_rate": 3.535731089018394e-05, "loss": 0.5111, "step": 368 }, { "epoch": 1.4954407294832825, "grad_norm": 0.4874542015233093, "learning_rate": 3.532088886237956e-05, "loss": 0.5166, "step": 369 }, { "epoch": 1.4994934143870315, "grad_norm": 0.5095607981513338, "learning_rate": 3.528434344224253e-05, "loss": 0.5222, "step": 370 }, { "epoch": 1.50354609929078, "grad_norm": 0.6068683781524951, "learning_rate": 3.524767492410464e-05, "loss": 0.5258, "step": 371 }, { "epoch": 1.5075987841945289, "grad_norm": 0.45995303775894525, "learning_rate": 3.521088360328908e-05, "loss": 0.5135, "step": 372 }, { "epoch": 1.5116514690982776, "grad_norm": 0.5402085099617082, "learning_rate": 3.517396977610811e-05, "loss": 0.5412, "step": 373 }, { "epoch": 1.5157041540020262, "grad_norm": 0.4117225221508349, "learning_rate": 3.5136933739860595e-05, "loss": 0.5197, "step": 374 }, { "epoch": 1.5197568389057752, "grad_norm": 0.5218056071265279, "learning_rate": 3.509977579282971e-05, "loss": 0.5418, "step": 375 }, { "epoch": 1.5238095238095237, "grad_norm": 0.4599303269519447, "learning_rate": 3.5062496234280424e-05, "loss": 0.5179, "step": 376 }, { "epoch": 1.5278622087132725, "grad_norm": 0.5466822045290498, "learning_rate": 3.502509536445719e-05, "loss": 0.5246, "step": 377 }, { "epoch": 1.5319148936170213, "grad_norm": 0.6238225853486538, "learning_rate": 3.498757348458147e-05, "loss": 0.5208, "step": 378 }, { "epoch": 1.53596757852077, "grad_norm": 0.41285087503838497, "learning_rate": 3.4949930896849324e-05, "loss": 0.5187, "step": 379 }, { "epoch": 1.5400202634245188, "grad_norm": 0.5434664565549008, "learning_rate": 3.491216790442899e-05, "loss": 0.5235, "step": 380 }, { "epoch": 1.5440729483282674, "grad_norm": 0.49047921137476336, "learning_rate": 3.487428481145839e-05, "loss": 0.5023, "step": 381 }, { "epoch": 1.5481256332320164, "grad_norm": 0.4792556828302923, "learning_rate": 3.483628192304278e-05, "loss": 0.5353, "step": 382 }, { "epoch": 1.552178318135765, "grad_norm": 0.5966200174699883, "learning_rate": 3.479815954525219e-05, "loss": 0.513, "step": 383 }, { "epoch": 1.5562310030395137, "grad_norm": 0.3972614524729954, "learning_rate": 3.475991798511899e-05, "loss": 0.5273, "step": 384 }, { "epoch": 1.5602836879432624, "grad_norm": 0.4959026982966128, "learning_rate": 3.4721557550635464e-05, "loss": 0.4951, "step": 385 }, { "epoch": 1.564336372847011, "grad_norm": 0.4191241509131936, "learning_rate": 3.468307855075128e-05, "loss": 0.5134, "step": 386 }, { "epoch": 1.56838905775076, "grad_norm": 0.49166278923604667, "learning_rate": 3.4644481295371005e-05, "loss": 0.5173, "step": 387 }, { "epoch": 1.5724417426545085, "grad_norm": 0.4820763565102606, "learning_rate": 3.460576609535163e-05, "loss": 0.5058, "step": 388 }, { "epoch": 1.5764944275582573, "grad_norm": 0.6365641641242409, "learning_rate": 3.456693326250006e-05, "loss": 0.5174, "step": 389 }, { "epoch": 1.580547112462006, "grad_norm": 0.5399204640668317, "learning_rate": 3.452798310957058e-05, "loss": 0.5156, "step": 390 }, { "epoch": 1.5845997973657548, "grad_norm": 0.6929809668016618, "learning_rate": 3.4488915950262386e-05, "loss": 0.517, "step": 391 }, { "epoch": 1.5886524822695036, "grad_norm": 0.6069426281857588, "learning_rate": 3.4449732099216985e-05, "loss": 0.5131, "step": 392 }, { "epoch": 1.5927051671732522, "grad_norm": 0.5443770799697926, "learning_rate": 3.441043187201574e-05, "loss": 0.5204, "step": 393 }, { "epoch": 1.5967578520770012, "grad_norm": 0.5423603378079402, "learning_rate": 3.437101558517728e-05, "loss": 0.5346, "step": 394 }, { "epoch": 1.6008105369807497, "grad_norm": 0.46439672944439964, "learning_rate": 3.433148355615496e-05, "loss": 0.5205, "step": 395 }, { "epoch": 1.6048632218844985, "grad_norm": 0.49156320237624823, "learning_rate": 3.4291836103334294e-05, "loss": 0.5415, "step": 396 }, { "epoch": 1.6089159067882473, "grad_norm": 0.4985362944083813, "learning_rate": 3.425207354603043e-05, "loss": 0.5465, "step": 397 }, { "epoch": 1.6129685916919958, "grad_norm": 0.4239378890163982, "learning_rate": 3.421219620448553e-05, "loss": 0.5387, "step": 398 }, { "epoch": 1.6170212765957448, "grad_norm": 0.523449987542341, "learning_rate": 3.417220439986623e-05, "loss": 0.5378, "step": 399 }, { "epoch": 1.6210739614994933, "grad_norm": 0.5239062023209914, "learning_rate": 3.4132098454261024e-05, "loss": 0.504, "step": 400 }, { "epoch": 1.6251266464032421, "grad_norm": 0.4278704882790379, "learning_rate": 3.4091878690677676e-05, "loss": 0.5156, "step": 401 }, { "epoch": 1.6291793313069909, "grad_norm": 0.6282985524545994, "learning_rate": 3.405154543304065e-05, "loss": 0.5336, "step": 402 }, { "epoch": 1.6332320162107397, "grad_norm": 0.47735699409054044, "learning_rate": 3.401109900618843e-05, "loss": 0.5291, "step": 403 }, { "epoch": 1.6372847011144884, "grad_norm": 0.6370109173024822, "learning_rate": 3.3970539735870996e-05, "loss": 0.5403, "step": 404 }, { "epoch": 1.641337386018237, "grad_norm": 0.43771744904293863, "learning_rate": 3.392986794874714e-05, "loss": 0.5192, "step": 405 }, { "epoch": 1.645390070921986, "grad_norm": 0.5830144740280944, "learning_rate": 3.388908397238184e-05, "loss": 0.5479, "step": 406 }, { "epoch": 1.6494427558257345, "grad_norm": 0.4709545357560335, "learning_rate": 3.384818813524362e-05, "loss": 0.5077, "step": 407 }, { "epoch": 1.6534954407294833, "grad_norm": 0.533680299031102, "learning_rate": 3.380718076670195e-05, "loss": 0.5328, "step": 408 }, { "epoch": 1.657548125633232, "grad_norm": 0.4800510860698552, "learning_rate": 3.376606219702454e-05, "loss": 0.5119, "step": 409 }, { "epoch": 1.6616008105369806, "grad_norm": 0.46192558495254865, "learning_rate": 3.372483275737468e-05, "loss": 0.526, "step": 410 }, { "epoch": 1.6656534954407296, "grad_norm": 0.4278490296945421, "learning_rate": 3.368349277980861e-05, "loss": 0.5128, "step": 411 }, { "epoch": 1.6697061803444782, "grad_norm": 0.5016325219235511, "learning_rate": 3.3642042597272844e-05, "loss": 0.5289, "step": 412 }, { "epoch": 1.673758865248227, "grad_norm": 0.5031776444064212, "learning_rate": 3.360048254360144e-05, "loss": 0.5222, "step": 413 }, { "epoch": 1.6778115501519757, "grad_norm": 0.4854305552137159, "learning_rate": 3.355881295351336e-05, "loss": 0.528, "step": 414 }, { "epoch": 1.6818642350557245, "grad_norm": 0.4733493254723261, "learning_rate": 3.351703416260975e-05, "loss": 0.5215, "step": 415 }, { "epoch": 1.6859169199594732, "grad_norm": 0.46328747017262467, "learning_rate": 3.347514650737126e-05, "loss": 0.5148, "step": 416 }, { "epoch": 1.6899696048632218, "grad_norm": 0.45673457256223376, "learning_rate": 3.3433150325155295e-05, "loss": 0.5109, "step": 417 }, { "epoch": 1.6940222897669708, "grad_norm": 0.45121040157866904, "learning_rate": 3.339104595419334e-05, "loss": 0.5307, "step": 418 }, { "epoch": 1.6980749746707193, "grad_norm": 0.4599716500280817, "learning_rate": 3.3348833733588204e-05, "loss": 0.5093, "step": 419 }, { "epoch": 1.702127659574468, "grad_norm": 0.5244704449142992, "learning_rate": 3.3306514003311305e-05, "loss": 0.54, "step": 420 }, { "epoch": 1.7061803444782169, "grad_norm": 0.49039850604531393, "learning_rate": 3.326408710419996e-05, "loss": 0.5146, "step": 421 }, { "epoch": 1.7102330293819654, "grad_norm": 0.49155803145386423, "learning_rate": 3.322155337795454e-05, "loss": 0.5428, "step": 422 }, { "epoch": 1.7142857142857144, "grad_norm": 0.4499724692021963, "learning_rate": 3.317891316713587e-05, "loss": 0.5218, "step": 423 }, { "epoch": 1.718338399189463, "grad_norm": 0.4440815719938451, "learning_rate": 3.313616681516231e-05, "loss": 0.5246, "step": 424 }, { "epoch": 1.7223910840932117, "grad_norm": 0.42270697927834755, "learning_rate": 3.309331466630713e-05, "loss": 0.5328, "step": 425 }, { "epoch": 1.7264437689969605, "grad_norm": 0.4678406893179575, "learning_rate": 3.305035706569563e-05, "loss": 0.501, "step": 426 }, { "epoch": 1.7304964539007093, "grad_norm": 0.4489905142839489, "learning_rate": 3.3007294359302433e-05, "loss": 0.5188, "step": 427 }, { "epoch": 1.734549138804458, "grad_norm": 0.41365173741361466, "learning_rate": 3.296412689394864e-05, "loss": 0.5069, "step": 428 }, { "epoch": 1.7386018237082066, "grad_norm": 0.46087665919684145, "learning_rate": 3.292085501729909e-05, "loss": 0.5444, "step": 429 }, { "epoch": 1.7426545086119554, "grad_norm": 0.4950981802616613, "learning_rate": 3.2877479077859534e-05, "loss": 0.5287, "step": 430 }, { "epoch": 1.7467071935157041, "grad_norm": 0.4329820173989564, "learning_rate": 3.283399942497381e-05, "loss": 0.5366, "step": 431 }, { "epoch": 1.750759878419453, "grad_norm": 0.5329613098901713, "learning_rate": 3.279041640882108e-05, "loss": 0.5197, "step": 432 }, { "epoch": 1.7548125633232017, "grad_norm": 0.4742677154402732, "learning_rate": 3.2746730380412964e-05, "loss": 0.5249, "step": 433 }, { "epoch": 1.7588652482269502, "grad_norm": 0.47577746586168224, "learning_rate": 3.2702941691590726e-05, "loss": 0.4988, "step": 434 }, { "epoch": 1.7629179331306992, "grad_norm": 0.9851965771168365, "learning_rate": 3.265905069502244e-05, "loss": 0.5321, "step": 435 }, { "epoch": 1.7669706180344478, "grad_norm": 0.4823979888760002, "learning_rate": 3.261505774420016e-05, "loss": 0.5189, "step": 436 }, { "epoch": 1.7710233029381965, "grad_norm": 0.455205134651666, "learning_rate": 3.257096319343707e-05, "loss": 0.5296, "step": 437 }, { "epoch": 1.7750759878419453, "grad_norm": 0.44071369522770004, "learning_rate": 3.2526767397864614e-05, "loss": 0.5435, "step": 438 }, { "epoch": 1.7791286727456939, "grad_norm": 0.6251863510623925, "learning_rate": 3.248247071342966e-05, "loss": 0.5292, "step": 439 }, { "epoch": 1.7831813576494429, "grad_norm": 5.237741963408119, "learning_rate": 3.243807349689161e-05, "loss": 0.5072, "step": 440 }, { "epoch": 1.7872340425531914, "grad_norm": 0.6028285059583506, "learning_rate": 3.2393576105819544e-05, "loss": 0.5275, "step": 441 }, { "epoch": 1.7912867274569402, "grad_norm": 0.45288379869363454, "learning_rate": 3.2348978898589333e-05, "loss": 0.5346, "step": 442 }, { "epoch": 1.795339412360689, "grad_norm": 0.44929836920429317, "learning_rate": 3.230428223438075e-05, "loss": 0.5252, "step": 443 }, { "epoch": 1.7993920972644377, "grad_norm": 0.426956744807085, "learning_rate": 3.225948647317459e-05, "loss": 0.5136, "step": 444 }, { "epoch": 1.8034447821681865, "grad_norm": 0.4560814759161261, "learning_rate": 3.2214591975749745e-05, "loss": 0.5271, "step": 445 }, { "epoch": 1.807497467071935, "grad_norm": 0.4522517163656964, "learning_rate": 3.216959910368034e-05, "loss": 0.5181, "step": 446 }, { "epoch": 1.811550151975684, "grad_norm": 0.498296326590016, "learning_rate": 3.212450821933277e-05, "loss": 0.5025, "step": 447 }, { "epoch": 1.8156028368794326, "grad_norm": 4.4486548801132875, "learning_rate": 3.207931968586281e-05, "loss": 0.535, "step": 448 }, { "epoch": 1.8196555217831814, "grad_norm": 0.575035701044211, "learning_rate": 3.203403386721272e-05, "loss": 0.5136, "step": 449 }, { "epoch": 1.8237082066869301, "grad_norm": 0.4563880710907371, "learning_rate": 3.1988651128108245e-05, "loss": 0.553, "step": 450 }, { "epoch": 1.8277608915906787, "grad_norm": 0.4588178359675035, "learning_rate": 3.194317183405573e-05, "loss": 0.522, "step": 451 }, { "epoch": 1.8318135764944277, "grad_norm": 0.4610151142830939, "learning_rate": 3.189759635133914e-05, "loss": 0.5262, "step": 452 }, { "epoch": 1.8358662613981762, "grad_norm": 0.47106972053347146, "learning_rate": 3.185192504701718e-05, "loss": 0.5055, "step": 453 }, { "epoch": 1.839918946301925, "grad_norm": 0.4996514947110662, "learning_rate": 3.1806158288920234e-05, "loss": 0.5278, "step": 454 }, { "epoch": 1.8439716312056738, "grad_norm": 0.4447332425452821, "learning_rate": 3.1760296445647477e-05, "loss": 0.5187, "step": 455 }, { "epoch": 1.8480243161094225, "grad_norm": 0.436025433182334, "learning_rate": 3.1714339886563896e-05, "loss": 0.5103, "step": 456 }, { "epoch": 1.8520770010131713, "grad_norm": 0.4435911283290316, "learning_rate": 3.166828898179731e-05, "loss": 0.5268, "step": 457 }, { "epoch": 1.8561296859169198, "grad_norm": 0.4755519379825723, "learning_rate": 3.162214410223536e-05, "loss": 0.5367, "step": 458 }, { "epoch": 1.8601823708206688, "grad_norm": 0.43745331518260105, "learning_rate": 3.157590561952257e-05, "loss": 0.5054, "step": 459 }, { "epoch": 1.8642350557244174, "grad_norm": 0.506874812204114, "learning_rate": 3.152957390605732e-05, "loss": 0.5467, "step": 460 }, { "epoch": 1.8682877406281662, "grad_norm": 0.4563562182319296, "learning_rate": 3.148314933498886e-05, "loss": 0.5103, "step": 461 }, { "epoch": 1.872340425531915, "grad_norm": 0.511279090204102, "learning_rate": 3.143663228021431e-05, "loss": 0.5159, "step": 462 }, { "epoch": 1.8763931104356635, "grad_norm": 0.5210563427852847, "learning_rate": 3.1390023116375624e-05, "loss": 0.5289, "step": 463 }, { "epoch": 1.8804457953394125, "grad_norm": 0.4216133282995977, "learning_rate": 3.134332221885661e-05, "loss": 0.5073, "step": 464 }, { "epoch": 1.884498480243161, "grad_norm": 0.5109875296599887, "learning_rate": 3.129652996377987e-05, "loss": 0.5374, "step": 465 }, { "epoch": 1.8885511651469098, "grad_norm": 0.4398826582348227, "learning_rate": 3.12496467280038e-05, "loss": 0.5152, "step": 466 }, { "epoch": 1.8926038500506586, "grad_norm": 0.5990306347700444, "learning_rate": 3.120267288911952e-05, "loss": 0.518, "step": 467 }, { "epoch": 1.8966565349544073, "grad_norm": 0.4678944678458127, "learning_rate": 3.11556088254479e-05, "loss": 0.5484, "step": 468 }, { "epoch": 1.900709219858156, "grad_norm": 0.586414211710391, "learning_rate": 3.11084549160364e-05, "loss": 0.543, "step": 469 }, { "epoch": 1.9047619047619047, "grad_norm": 0.5029556906315458, "learning_rate": 3.106121154065615e-05, "loss": 0.5309, "step": 470 }, { "epoch": 1.9088145896656536, "grad_norm": 0.6188263570301109, "learning_rate": 3.1013879079798805e-05, "loss": 0.5239, "step": 471 }, { "epoch": 1.9128672745694022, "grad_norm": 0.5197232110656221, "learning_rate": 3.096645791467348e-05, "loss": 0.5316, "step": 472 }, { "epoch": 1.916919959473151, "grad_norm": 0.5049144817665914, "learning_rate": 3.091894842720373e-05, "loss": 0.507, "step": 473 }, { "epoch": 1.9209726443768997, "grad_norm": 0.4872513269437638, "learning_rate": 3.0871351000024425e-05, "loss": 0.5675, "step": 474 }, { "epoch": 1.9250253292806483, "grad_norm": 0.523793855618941, "learning_rate": 3.0823666016478716e-05, "loss": 0.5095, "step": 475 }, { "epoch": 1.9290780141843973, "grad_norm": 0.4475698418425971, "learning_rate": 3.0775893860614896e-05, "loss": 0.5385, "step": 476 }, { "epoch": 1.9331306990881458, "grad_norm": 0.5248101484565839, "learning_rate": 3.0728034917183336e-05, "loss": 0.5346, "step": 477 }, { "epoch": 1.9371833839918946, "grad_norm": 0.43479752861596394, "learning_rate": 3.06800895716334e-05, "loss": 0.5341, "step": 478 }, { "epoch": 1.9412360688956434, "grad_norm": 0.4753365099371603, "learning_rate": 3.063205821011029e-05, "loss": 0.4991, "step": 479 }, { "epoch": 1.9452887537993921, "grad_norm": 0.43641949097561217, "learning_rate": 3.0583941219452016e-05, "loss": 0.5293, "step": 480 }, { "epoch": 1.949341438703141, "grad_norm": 0.4318038415988742, "learning_rate": 3.053573898718618e-05, "loss": 0.5175, "step": 481 }, { "epoch": 1.9533941236068895, "grad_norm": 0.43194074981805536, "learning_rate": 3.0487451901526956e-05, "loss": 0.5242, "step": 482 }, { "epoch": 1.9574468085106385, "grad_norm": 0.4352916731275262, "learning_rate": 3.0439080351371875e-05, "loss": 0.5114, "step": 483 }, { "epoch": 1.961499493414387, "grad_norm": 0.5675741468391975, "learning_rate": 3.0390624726298764e-05, "loss": 0.5358, "step": 484 }, { "epoch": 1.9655521783181358, "grad_norm": 0.4164535121026274, "learning_rate": 3.034208541656255e-05, "loss": 0.5448, "step": 485 }, { "epoch": 1.9696048632218845, "grad_norm": 0.5006076462431339, "learning_rate": 3.029346281309218e-05, "loss": 0.5083, "step": 486 }, { "epoch": 1.973657548125633, "grad_norm": 0.45032708293165896, "learning_rate": 3.0244757307487415e-05, "loss": 0.5368, "step": 487 }, { "epoch": 1.977710233029382, "grad_norm": 0.46440525247323666, "learning_rate": 3.019596929201569e-05, "loss": 0.5178, "step": 488 }, { "epoch": 1.9817629179331306, "grad_norm": 0.4370803534776703, "learning_rate": 3.0147099159608985e-05, "loss": 0.5368, "step": 489 }, { "epoch": 1.9858156028368794, "grad_norm": 0.4779198932334461, "learning_rate": 3.0098147303860616e-05, "loss": 0.5186, "step": 490 }, { "epoch": 1.9898682877406282, "grad_norm": 0.3914689882946684, "learning_rate": 3.0049114119022117e-05, "loss": 0.5313, "step": 491 }, { "epoch": 1.993920972644377, "grad_norm": 0.52269164790699, "learning_rate": 3.0000000000000004e-05, "loss": 0.5219, "step": 492 }, { "epoch": 1.9979736575481257, "grad_norm": 0.41065354137650834, "learning_rate": 2.995080534235264e-05, "loss": 0.5115, "step": 493 }, { "epoch": 2.0020263424518743, "grad_norm": 0.6232621074004968, "learning_rate": 2.9901530542287044e-05, "loss": 0.453, "step": 494 }, { "epoch": 2.0060790273556233, "grad_norm": 0.8169909853325651, "learning_rate": 2.9852175996655676e-05, "loss": 0.3995, "step": 495 }, { "epoch": 2.010131712259372, "grad_norm": 1.65561844571941, "learning_rate": 2.980274210295326e-05, "loss": 0.3993, "step": 496 }, { "epoch": 2.0141843971631204, "grad_norm": 0.5510670332038249, "learning_rate": 2.9753229259313578e-05, "loss": 0.3809, "step": 497 }, { "epoch": 2.0182370820668694, "grad_norm": 0.5902591145076758, "learning_rate": 2.9703637864506274e-05, "loss": 0.388, "step": 498 }, { "epoch": 2.022289766970618, "grad_norm": 0.581870188636675, "learning_rate": 2.965396831793362e-05, "loss": 0.3923, "step": 499 }, { "epoch": 2.026342451874367, "grad_norm": 0.5122119525731773, "learning_rate": 2.9604221019627316e-05, "loss": 0.3924, "step": 500 }, { "epoch": 2.0303951367781155, "grad_norm": 0.6369001201435273, "learning_rate": 2.955439637024526e-05, "loss": 0.4021, "step": 501 }, { "epoch": 2.0344478216818644, "grad_norm": 0.5607219551159003, "learning_rate": 2.9504494771068334e-05, "loss": 0.3863, "step": 502 }, { "epoch": 2.038500506585613, "grad_norm": 0.5690904246439554, "learning_rate": 2.9454516623997156e-05, "loss": 0.3982, "step": 503 }, { "epoch": 2.0425531914893615, "grad_norm": 0.5606348830350215, "learning_rate": 2.9404462331548847e-05, "loss": 0.3895, "step": 504 }, { "epoch": 2.0466058763931105, "grad_norm": 0.4868023717582465, "learning_rate": 2.93543322968538e-05, "loss": 0.3837, "step": 505 }, { "epoch": 2.050658561296859, "grad_norm": 0.47931255663885713, "learning_rate": 2.9304126923652428e-05, "loss": 0.3664, "step": 506 }, { "epoch": 2.054711246200608, "grad_norm": 0.5223096925986057, "learning_rate": 2.9253846616291896e-05, "loss": 0.3757, "step": 507 }, { "epoch": 2.0587639311043566, "grad_norm": 0.49467389021849756, "learning_rate": 2.9203491779722896e-05, "loss": 0.3933, "step": 508 }, { "epoch": 2.062816616008105, "grad_norm": 0.4782933391638284, "learning_rate": 2.9153062819496357e-05, "loss": 0.3704, "step": 509 }, { "epoch": 2.066869300911854, "grad_norm": 0.45425163866874996, "learning_rate": 2.9102560141760178e-05, "loss": 0.3855, "step": 510 }, { "epoch": 2.0709219858156027, "grad_norm": 0.4672148090714988, "learning_rate": 2.9051984153256004e-05, "loss": 0.3812, "step": 511 }, { "epoch": 2.0749746707193517, "grad_norm": 0.4586673041925491, "learning_rate": 2.900133526131588e-05, "loss": 0.3804, "step": 512 }, { "epoch": 2.0790273556231003, "grad_norm": 0.4470522437231022, "learning_rate": 2.8950613873859025e-05, "loss": 0.3584, "step": 513 }, { "epoch": 2.0830800405268493, "grad_norm": 0.4840466133147679, "learning_rate": 2.8899820399388515e-05, "loss": 0.3703, "step": 514 }, { "epoch": 2.087132725430598, "grad_norm": 0.43699024485975313, "learning_rate": 2.8848955246988012e-05, "loss": 0.3697, "step": 515 }, { "epoch": 2.0911854103343464, "grad_norm": 0.4617029420399355, "learning_rate": 2.879801882631847e-05, "loss": 0.3802, "step": 516 }, { "epoch": 2.0952380952380953, "grad_norm": 0.45405988329926195, "learning_rate": 2.8747011547614808e-05, "loss": 0.3998, "step": 517 }, { "epoch": 2.099290780141844, "grad_norm": 0.44440396091154216, "learning_rate": 2.8695933821682635e-05, "loss": 0.37, "step": 518 }, { "epoch": 2.103343465045593, "grad_norm": 0.4762703853920394, "learning_rate": 2.864478605989494e-05, "loss": 0.3718, "step": 519 }, { "epoch": 2.1073961499493414, "grad_norm": 0.4150592525523646, "learning_rate": 2.8593568674188765e-05, "loss": 0.3767, "step": 520 }, { "epoch": 2.11144883485309, "grad_norm": 0.4725077696341366, "learning_rate": 2.8542282077061892e-05, "loss": 0.3848, "step": 521 }, { "epoch": 2.115501519756839, "grad_norm": 0.42378037803754093, "learning_rate": 2.8490926681569523e-05, "loss": 0.3726, "step": 522 }, { "epoch": 2.1195542046605875, "grad_norm": 0.38885784145222896, "learning_rate": 2.8439502901320956e-05, "loss": 0.3885, "step": 523 }, { "epoch": 2.1236068895643365, "grad_norm": 0.4415263609638792, "learning_rate": 2.8388011150476237e-05, "loss": 0.3906, "step": 524 }, { "epoch": 2.127659574468085, "grad_norm": 0.41640563801208946, "learning_rate": 2.8336451843742866e-05, "loss": 0.3598, "step": 525 }, { "epoch": 2.1317122593718336, "grad_norm": 0.4096956476053644, "learning_rate": 2.8284825396372387e-05, "loss": 0.3842, "step": 526 }, { "epoch": 2.1357649442755826, "grad_norm": 0.4377291728632232, "learning_rate": 2.8233132224157132e-05, "loss": 0.3887, "step": 527 }, { "epoch": 2.139817629179331, "grad_norm": 0.3737306695119243, "learning_rate": 2.8181372743426805e-05, "loss": 0.3648, "step": 528 }, { "epoch": 2.14387031408308, "grad_norm": 0.42100018353041196, "learning_rate": 2.8129547371045128e-05, "loss": 0.3744, "step": 529 }, { "epoch": 2.1479229989868287, "grad_norm": 0.41436306962303654, "learning_rate": 2.8077656524406534e-05, "loss": 0.3953, "step": 530 }, { "epoch": 2.1519756838905777, "grad_norm": 0.3858696987436117, "learning_rate": 2.802570062143278e-05, "loss": 0.3765, "step": 531 }, { "epoch": 2.1560283687943262, "grad_norm": 0.4124078601251155, "learning_rate": 2.7973680080569555e-05, "loss": 0.3693, "step": 532 }, { "epoch": 2.160081053698075, "grad_norm": 0.4266867491757614, "learning_rate": 2.792159532078314e-05, "loss": 0.3664, "step": 533 }, { "epoch": 2.164133738601824, "grad_norm": 0.3978170466321553, "learning_rate": 2.7869446761557033e-05, "loss": 0.3816, "step": 534 }, { "epoch": 2.1681864235055723, "grad_norm": 0.43102734791598346, "learning_rate": 2.781723482288857e-05, "loss": 0.3825, "step": 535 }, { "epoch": 2.1722391084093213, "grad_norm": 0.3901304725972472, "learning_rate": 2.7764959925285517e-05, "loss": 0.3788, "step": 536 }, { "epoch": 2.17629179331307, "grad_norm": 0.4865783173738111, "learning_rate": 2.771262248976272e-05, "loss": 0.3857, "step": 537 }, { "epoch": 2.180344478216819, "grad_norm": 0.3785043876040034, "learning_rate": 2.7660222937838677e-05, "loss": 0.3766, "step": 538 }, { "epoch": 2.1843971631205674, "grad_norm": 0.43871924157027203, "learning_rate": 2.7607761691532186e-05, "loss": 0.36, "step": 539 }, { "epoch": 2.188449848024316, "grad_norm": 0.4032015416906201, "learning_rate": 2.7555239173358916e-05, "loss": 0.3858, "step": 540 }, { "epoch": 2.192502532928065, "grad_norm": 0.42985166613333153, "learning_rate": 2.7502655806328e-05, "loss": 0.3801, "step": 541 }, { "epoch": 2.1965552178318135, "grad_norm": 0.4081432867416322, "learning_rate": 2.7450012013938648e-05, "loss": 0.3796, "step": 542 }, { "epoch": 2.2006079027355625, "grad_norm": 0.4105681252274914, "learning_rate": 2.739730822017673e-05, "loss": 0.3871, "step": 543 }, { "epoch": 2.204660587639311, "grad_norm": 0.4405657516618478, "learning_rate": 2.7344544849511355e-05, "loss": 0.3871, "step": 544 }, { "epoch": 2.2087132725430596, "grad_norm": 0.40420869178467833, "learning_rate": 2.7291722326891456e-05, "loss": 0.3947, "step": 545 }, { "epoch": 2.2127659574468086, "grad_norm": 0.41475963587342235, "learning_rate": 2.723884107774236e-05, "loss": 0.3766, "step": 546 }, { "epoch": 2.216818642350557, "grad_norm": 0.4352827849622015, "learning_rate": 2.718590152796239e-05, "loss": 0.3999, "step": 547 }, { "epoch": 2.220871327254306, "grad_norm": 0.38854387845945204, "learning_rate": 2.71329041039194e-05, "loss": 0.3651, "step": 548 }, { "epoch": 2.2249240121580547, "grad_norm": 0.4350894454142731, "learning_rate": 2.7079849232447357e-05, "loss": 0.3852, "step": 549 }, { "epoch": 2.2289766970618032, "grad_norm": 0.4286420643863448, "learning_rate": 2.7026737340842895e-05, "loss": 0.3859, "step": 550 }, { "epoch": 2.2330293819655522, "grad_norm": 0.40829811576315933, "learning_rate": 2.697356885686189e-05, "loss": 0.3897, "step": 551 }, { "epoch": 2.237082066869301, "grad_norm": 0.4119258956286351, "learning_rate": 2.6920344208716014e-05, "loss": 0.396, "step": 552 }, { "epoch": 2.2411347517730498, "grad_norm": 0.40459874467202434, "learning_rate": 2.6867063825069252e-05, "loss": 0.3646, "step": 553 }, { "epoch": 2.2451874366767983, "grad_norm": 0.44324114811035326, "learning_rate": 2.6813728135034494e-05, "loss": 0.3832, "step": 554 }, { "epoch": 2.2492401215805473, "grad_norm": 0.3738346466608523, "learning_rate": 2.6760337568170056e-05, "loss": 0.3819, "step": 555 }, { "epoch": 2.253292806484296, "grad_norm": 0.45453455890313166, "learning_rate": 2.6706892554476226e-05, "loss": 0.3761, "step": 556 }, { "epoch": 2.2573454913880444, "grad_norm": 0.3943998611110839, "learning_rate": 2.6653393524391795e-05, "loss": 0.3882, "step": 557 }, { "epoch": 2.2613981762917934, "grad_norm": 0.41387653919697004, "learning_rate": 2.6599840908790592e-05, "loss": 0.3727, "step": 558 }, { "epoch": 2.265450861195542, "grad_norm": 0.3986327009516797, "learning_rate": 2.6546235138978028e-05, "loss": 0.3634, "step": 559 }, { "epoch": 2.269503546099291, "grad_norm": 0.48499203758999465, "learning_rate": 2.6492576646687597e-05, "loss": 0.3857, "step": 560 }, { "epoch": 2.2735562310030395, "grad_norm": 0.4226373434122471, "learning_rate": 2.6438865864077425e-05, "loss": 0.3711, "step": 561 }, { "epoch": 2.2776089159067885, "grad_norm": 0.44094398538075524, "learning_rate": 2.6385103223726766e-05, "loss": 0.3726, "step": 562 }, { "epoch": 2.281661600810537, "grad_norm": 0.42810302434452924, "learning_rate": 2.6331289158632537e-05, "loss": 0.3849, "step": 563 }, { "epoch": 2.2857142857142856, "grad_norm": 0.4184503377943871, "learning_rate": 2.6277424102205817e-05, "loss": 0.37, "step": 564 }, { "epoch": 2.2897669706180346, "grad_norm": 0.4432225616112314, "learning_rate": 2.6223508488268374e-05, "loss": 0.3696, "step": 565 }, { "epoch": 2.293819655521783, "grad_norm": 0.38533088289882106, "learning_rate": 2.6169542751049148e-05, "loss": 0.3846, "step": 566 }, { "epoch": 2.297872340425532, "grad_norm": 0.45459020294460795, "learning_rate": 2.6115527325180754e-05, "loss": 0.3483, "step": 567 }, { "epoch": 2.3019250253292807, "grad_norm": 0.3987525159041936, "learning_rate": 2.606146264569603e-05, "loss": 0.3797, "step": 568 }, { "epoch": 2.305977710233029, "grad_norm": 0.3917876397747245, "learning_rate": 2.6007349148024447e-05, "loss": 0.3636, "step": 569 }, { "epoch": 2.310030395136778, "grad_norm": 0.4248791571615101, "learning_rate": 2.5953187267988694e-05, "loss": 0.3773, "step": 570 }, { "epoch": 2.3140830800405268, "grad_norm": 0.39213120685951824, "learning_rate": 2.5898977441801097e-05, "loss": 0.375, "step": 571 }, { "epoch": 2.3181357649442758, "grad_norm": 0.4188292988155098, "learning_rate": 2.584472010606015e-05, "loss": 0.3746, "step": 572 }, { "epoch": 2.3221884498480243, "grad_norm": 0.3963465963177131, "learning_rate": 2.5790415697746976e-05, "loss": 0.3682, "step": 573 }, { "epoch": 2.326241134751773, "grad_norm": 0.42230860830833267, "learning_rate": 2.5736064654221808e-05, "loss": 0.3845, "step": 574 }, { "epoch": 2.330293819655522, "grad_norm": 0.4436008807056159, "learning_rate": 2.568166741322048e-05, "loss": 0.3591, "step": 575 }, { "epoch": 2.3343465045592704, "grad_norm": 0.37066010387279286, "learning_rate": 2.56272244128509e-05, "loss": 0.3612, "step": 576 }, { "epoch": 2.3383991894630194, "grad_norm": 0.4330675968766995, "learning_rate": 2.55727360915895e-05, "loss": 0.3867, "step": 577 }, { "epoch": 2.342451874366768, "grad_norm": 0.40880093907937803, "learning_rate": 2.5518202888277734e-05, "loss": 0.3786, "step": 578 }, { "epoch": 2.3465045592705165, "grad_norm": 0.39795064444132017, "learning_rate": 2.5463625242118523e-05, "loss": 0.3813, "step": 579 }, { "epoch": 2.3505572441742655, "grad_norm": 0.37522536620671515, "learning_rate": 2.5409003592672723e-05, "loss": 0.3835, "step": 580 }, { "epoch": 2.354609929078014, "grad_norm": 0.4479217190524236, "learning_rate": 2.535433837985559e-05, "loss": 0.3824, "step": 581 }, { "epoch": 2.358662613981763, "grad_norm": 0.40930651198571455, "learning_rate": 2.529963004393324e-05, "loss": 0.3792, "step": 582 }, { "epoch": 2.3627152988855116, "grad_norm": 0.36076212305214456, "learning_rate": 2.524487902551908e-05, "loss": 0.378, "step": 583 }, { "epoch": 2.3667679837892606, "grad_norm": 0.42039817052177986, "learning_rate": 2.519008576557029e-05, "loss": 0.3687, "step": 584 }, { "epoch": 2.370820668693009, "grad_norm": 0.37379960596206885, "learning_rate": 2.5135250705384254e-05, "loss": 0.3664, "step": 585 }, { "epoch": 2.3748733535967577, "grad_norm": 0.4467751129733778, "learning_rate": 2.5080374286595007e-05, "loss": 0.371, "step": 586 }, { "epoch": 2.3789260385005067, "grad_norm": 0.4007386534063922, "learning_rate": 2.5025456951169677e-05, "loss": 0.3554, "step": 587 }, { "epoch": 2.382978723404255, "grad_norm": 0.4119635809316113, "learning_rate": 2.4970499141404942e-05, "loss": 0.378, "step": 588 }, { "epoch": 2.387031408308004, "grad_norm": 0.47346681867348134, "learning_rate": 2.491550129992345e-05, "loss": 0.3606, "step": 589 }, { "epoch": 2.3910840932117527, "grad_norm": 0.40564117950013207, "learning_rate": 2.486046386967024e-05, "loss": 0.3902, "step": 590 }, { "epoch": 2.3951367781155017, "grad_norm": 0.4190961363148275, "learning_rate": 2.4805387293909214e-05, "loss": 0.3615, "step": 591 }, { "epoch": 2.3991894630192503, "grad_norm": 0.44932026629769223, "learning_rate": 2.4750272016219552e-05, "loss": 0.3552, "step": 592 }, { "epoch": 2.403242147922999, "grad_norm": 0.4136435376168819, "learning_rate": 2.4695118480492114e-05, "loss": 0.3799, "step": 593 }, { "epoch": 2.407294832826748, "grad_norm": 0.47035995869422675, "learning_rate": 2.4639927130925898e-05, "loss": 0.3712, "step": 594 }, { "epoch": 2.4113475177304964, "grad_norm": 0.4262153307259335, "learning_rate": 2.458469841202444e-05, "loss": 0.3665, "step": 595 }, { "epoch": 2.4154002026342454, "grad_norm": 0.41518180585769826, "learning_rate": 2.452943276859226e-05, "loss": 0.3846, "step": 596 }, { "epoch": 2.419452887537994, "grad_norm": 0.41176549247240596, "learning_rate": 2.447413064573125e-05, "loss": 0.39, "step": 597 }, { "epoch": 2.4235055724417425, "grad_norm": 0.42071307008133824, "learning_rate": 2.4418792488837095e-05, "loss": 0.3671, "step": 598 }, { "epoch": 2.4275582573454915, "grad_norm": 0.39871906594638695, "learning_rate": 2.4363418743595713e-05, "loss": 0.3891, "step": 599 }, { "epoch": 2.43161094224924, "grad_norm": 0.43702924369234947, "learning_rate": 2.430800985597963e-05, "loss": 0.3909, "step": 600 }, { "epoch": 2.435663627152989, "grad_norm": 0.4131901920541675, "learning_rate": 2.4252566272244415e-05, "loss": 0.3664, "step": 601 }, { "epoch": 2.4397163120567376, "grad_norm": 0.4195389982623185, "learning_rate": 2.4197088438925063e-05, "loss": 0.365, "step": 602 }, { "epoch": 2.443768996960486, "grad_norm": 0.42836971921357075, "learning_rate": 2.4141576802832417e-05, "loss": 0.3764, "step": 603 }, { "epoch": 2.447821681864235, "grad_norm": 0.3818961441018969, "learning_rate": 2.408603181104957e-05, "loss": 0.3837, "step": 604 }, { "epoch": 2.4518743667679836, "grad_norm": 0.46811873730436787, "learning_rate": 2.4030453910928245e-05, "loss": 0.3775, "step": 605 }, { "epoch": 2.4559270516717326, "grad_norm": 0.382206133462594, "learning_rate": 2.397484355008521e-05, "loss": 0.3741, "step": 606 }, { "epoch": 2.459979736575481, "grad_norm": 0.4333455945048134, "learning_rate": 2.3919201176398662e-05, "loss": 0.3884, "step": 607 }, { "epoch": 2.46403242147923, "grad_norm": 0.3863605999991453, "learning_rate": 2.3863527238004633e-05, "loss": 0.4034, "step": 608 }, { "epoch": 2.4680851063829787, "grad_norm": 0.3772576840977968, "learning_rate": 2.380782218329337e-05, "loss": 0.3851, "step": 609 }, { "epoch": 2.4721377912867273, "grad_norm": 0.4101064024145213, "learning_rate": 2.3752086460905725e-05, "loss": 0.3816, "step": 610 }, { "epoch": 2.4761904761904763, "grad_norm": 0.40575792529637883, "learning_rate": 2.3696320519729544e-05, "loss": 0.3885, "step": 611 }, { "epoch": 2.480243161094225, "grad_norm": 0.3891190110820612, "learning_rate": 2.3640524808896045e-05, "loss": 0.3963, "step": 612 }, { "epoch": 2.484295845997974, "grad_norm": 0.3824125650383179, "learning_rate": 2.3584699777776222e-05, "loss": 0.3775, "step": 613 }, { "epoch": 2.4883485309017224, "grad_norm": 0.3822018624287662, "learning_rate": 2.3528845875977195e-05, "loss": 0.3712, "step": 614 }, { "epoch": 2.4924012158054714, "grad_norm": 0.3902267787396165, "learning_rate": 2.3472963553338614e-05, "loss": 0.372, "step": 615 }, { "epoch": 2.49645390070922, "grad_norm": 0.3617482440577049, "learning_rate": 2.341705325992901e-05, "loss": 0.3703, "step": 616 }, { "epoch": 2.5005065856129685, "grad_norm": 0.39054685343275136, "learning_rate": 2.336111544604222e-05, "loss": 0.3602, "step": 617 }, { "epoch": 2.5045592705167175, "grad_norm": 0.3735509393891408, "learning_rate": 2.33051505621937e-05, "loss": 0.3762, "step": 618 }, { "epoch": 2.508611955420466, "grad_norm": 0.35661656981457157, "learning_rate": 2.324915905911693e-05, "loss": 0.3745, "step": 619 }, { "epoch": 2.512664640324215, "grad_norm": 0.38820137263090165, "learning_rate": 2.319314138775977e-05, "loss": 0.3769, "step": 620 }, { "epoch": 2.5167173252279635, "grad_norm": 0.35358970141786616, "learning_rate": 2.3137097999280856e-05, "loss": 0.3768, "step": 621 }, { "epoch": 2.520770010131712, "grad_norm": 0.3895221568896916, "learning_rate": 2.308102934504593e-05, "loss": 0.3714, "step": 622 }, { "epoch": 2.524822695035461, "grad_norm": 0.37935152151278373, "learning_rate": 2.3024935876624222e-05, "loss": 0.3925, "step": 623 }, { "epoch": 2.5288753799392096, "grad_norm": 0.3763570799159414, "learning_rate": 2.2968818045784813e-05, "loss": 0.377, "step": 624 }, { "epoch": 2.5329280648429586, "grad_norm": 0.3708096374727324, "learning_rate": 2.2912676304493006e-05, "loss": 0.3812, "step": 625 }, { "epoch": 2.536980749746707, "grad_norm": 0.3819554217877225, "learning_rate": 2.2856511104906668e-05, "loss": 0.4035, "step": 626 }, { "epoch": 2.5410334346504557, "grad_norm": 0.36913526743289365, "learning_rate": 2.2800322899372586e-05, "loss": 0.3688, "step": 627 }, { "epoch": 2.5450861195542047, "grad_norm": 0.3639443937619455, "learning_rate": 2.2744112140422844e-05, "loss": 0.3791, "step": 628 }, { "epoch": 2.5491388044579533, "grad_norm": 0.4149934290729677, "learning_rate": 2.2687879280771177e-05, "loss": 0.3958, "step": 629 }, { "epoch": 2.5531914893617023, "grad_norm": 0.38347523579059295, "learning_rate": 2.26316247733093e-05, "loss": 0.3636, "step": 630 }, { "epoch": 2.557244174265451, "grad_norm": 0.4420509005241039, "learning_rate": 2.257534907110328e-05, "loss": 0.3959, "step": 631 }, { "epoch": 2.5612968591691994, "grad_norm": 0.408905711610069, "learning_rate": 2.2519052627389882e-05, "loss": 0.3766, "step": 632 }, { "epoch": 2.5653495440729484, "grad_norm": 0.37825266042953937, "learning_rate": 2.246273589557294e-05, "loss": 0.3849, "step": 633 }, { "epoch": 2.569402228976697, "grad_norm": 0.43414986147382434, "learning_rate": 2.240639932921966e-05, "loss": 0.3883, "step": 634 }, { "epoch": 2.573454913880446, "grad_norm": 0.3744659398071677, "learning_rate": 2.2350043382056995e-05, "loss": 0.3756, "step": 635 }, { "epoch": 2.5775075987841944, "grad_norm": 0.40986103144476926, "learning_rate": 2.2293668507968015e-05, "loss": 0.3681, "step": 636 }, { "epoch": 2.581560283687943, "grad_norm": 0.3996212073361045, "learning_rate": 2.2237275160988186e-05, "loss": 0.3798, "step": 637 }, { "epoch": 2.585612968591692, "grad_norm": 0.3793763813055075, "learning_rate": 2.2180863795301787e-05, "loss": 0.3861, "step": 638 }, { "epoch": 2.589665653495441, "grad_norm": 0.4005993878505897, "learning_rate": 2.212443486523819e-05, "loss": 0.3694, "step": 639 }, { "epoch": 2.5937183383991895, "grad_norm": 0.3899642945934973, "learning_rate": 2.2067988825268243e-05, "loss": 0.3941, "step": 640 }, { "epoch": 2.597771023302938, "grad_norm": 0.4038712054901919, "learning_rate": 2.2011526130000596e-05, "loss": 0.3784, "step": 641 }, { "epoch": 2.601823708206687, "grad_norm": 0.4120780054958312, "learning_rate": 2.1955047234178038e-05, "loss": 0.3906, "step": 642 }, { "epoch": 2.6058763931104356, "grad_norm": 0.37054887907501416, "learning_rate": 2.1898552592673825e-05, "loss": 0.366, "step": 643 }, { "epoch": 2.6099290780141846, "grad_norm": 0.39411090352456984, "learning_rate": 2.184204266048803e-05, "loss": 0.3764, "step": 644 }, { "epoch": 2.613981762917933, "grad_norm": 0.40547711641747647, "learning_rate": 2.1785517892743887e-05, "loss": 0.3779, "step": 645 }, { "epoch": 2.6180344478216817, "grad_norm": 0.37010071859343574, "learning_rate": 2.17289787446841e-05, "loss": 0.4027, "step": 646 }, { "epoch": 2.6220871327254307, "grad_norm": 0.37799910699161426, "learning_rate": 2.1672425671667198e-05, "loss": 0.3659, "step": 647 }, { "epoch": 2.6261398176291793, "grad_norm": 0.40366355092847167, "learning_rate": 2.161585912916385e-05, "loss": 0.3795, "step": 648 }, { "epoch": 2.6301925025329282, "grad_norm": 0.38310254282681644, "learning_rate": 2.1559279572753214e-05, "loss": 0.3594, "step": 649 }, { "epoch": 2.634245187436677, "grad_norm": 0.3883302189496693, "learning_rate": 2.1502687458119268e-05, "loss": 0.3968, "step": 650 }, { "epoch": 2.6382978723404253, "grad_norm": 0.3735177985957199, "learning_rate": 2.1446083241047116e-05, "loss": 0.392, "step": 651 }, { "epoch": 2.6423505572441743, "grad_norm": 0.36619361662693517, "learning_rate": 2.1389467377419333e-05, "loss": 0.3911, "step": 652 }, { "epoch": 2.646403242147923, "grad_norm": 0.3556681152065816, "learning_rate": 2.133284032321232e-05, "loss": 0.3948, "step": 653 }, { "epoch": 2.650455927051672, "grad_norm": 0.37492067817330393, "learning_rate": 2.1276202534492566e-05, "loss": 0.3822, "step": 654 }, { "epoch": 2.6545086119554204, "grad_norm": 0.3791878754761423, "learning_rate": 2.121955446741306e-05, "loss": 0.3557, "step": 655 }, { "epoch": 2.658561296859169, "grad_norm": 0.41548913876098637, "learning_rate": 2.1162896578209517e-05, "loss": 0.3695, "step": 656 }, { "epoch": 2.662613981762918, "grad_norm": 0.35442545340571024, "learning_rate": 2.1106229323196813e-05, "loss": 0.3727, "step": 657 }, { "epoch": 2.6666666666666665, "grad_norm": 0.3565427539064041, "learning_rate": 2.1049553158765214e-05, "loss": 0.3589, "step": 658 }, { "epoch": 2.6707193515704155, "grad_norm": 0.3746704132058309, "learning_rate": 2.0992868541376764e-05, "loss": 0.3974, "step": 659 }, { "epoch": 2.674772036474164, "grad_norm": 0.3791594215115498, "learning_rate": 2.093617592756158e-05, "loss": 0.3575, "step": 660 }, { "epoch": 2.6788247213779126, "grad_norm": 0.3710386307717811, "learning_rate": 2.0879475773914167e-05, "loss": 0.3801, "step": 661 }, { "epoch": 2.6828774062816616, "grad_norm": 0.36892767257957243, "learning_rate": 2.082276853708978e-05, "loss": 0.371, "step": 662 }, { "epoch": 2.6869300911854106, "grad_norm": 0.39783575774095603, "learning_rate": 2.076605467380071e-05, "loss": 0.3858, "step": 663 }, { "epoch": 2.690982776089159, "grad_norm": 0.3647315679168818, "learning_rate": 2.0709334640812613e-05, "loss": 0.4014, "step": 664 }, { "epoch": 2.6950354609929077, "grad_norm": 0.3484398498485764, "learning_rate": 2.0652608894940824e-05, "loss": 0.383, "step": 665 }, { "epoch": 2.6990881458966567, "grad_norm": 0.4013105776920568, "learning_rate": 2.0595877893046722e-05, "loss": 0.3851, "step": 666 }, { "epoch": 2.7031408308004052, "grad_norm": 0.36057351575739904, "learning_rate": 2.0539142092033985e-05, "loss": 0.3689, "step": 667 }, { "epoch": 2.7071935157041542, "grad_norm": 0.37345619593276425, "learning_rate": 2.048240194884496e-05, "loss": 0.3924, "step": 668 }, { "epoch": 2.711246200607903, "grad_norm": 0.40335554590301, "learning_rate": 2.042565792045695e-05, "loss": 0.3775, "step": 669 }, { "epoch": 2.7152988855116513, "grad_norm": 0.3644864047403148, "learning_rate": 2.036891046387857e-05, "loss": 0.371, "step": 670 }, { "epoch": 2.7193515704154003, "grad_norm": 0.38553621926411713, "learning_rate": 2.0312160036146036e-05, "loss": 0.379, "step": 671 }, { "epoch": 2.723404255319149, "grad_norm": 0.3811039494400777, "learning_rate": 2.025540709431948e-05, "loss": 0.3859, "step": 672 }, { "epoch": 2.727456940222898, "grad_norm": 0.365337052525446, "learning_rate": 2.0198652095479298e-05, "loss": 0.3882, "step": 673 }, { "epoch": 2.7315096251266464, "grad_norm": 0.35817396458331424, "learning_rate": 2.014189549672245e-05, "loss": 0.3787, "step": 674 }, { "epoch": 2.735562310030395, "grad_norm": 0.38239411741221413, "learning_rate": 2.0085137755158776e-05, "loss": 0.3418, "step": 675 }, { "epoch": 2.739614994934144, "grad_norm": 0.36510941017207393, "learning_rate": 2.0028379327907327e-05, "loss": 0.3725, "step": 676 }, { "epoch": 2.7436676798378925, "grad_norm": 0.3898901677976552, "learning_rate": 1.9971620672092676e-05, "loss": 0.4074, "step": 677 }, { "epoch": 2.7477203647416415, "grad_norm": 0.3862996385449035, "learning_rate": 1.991486224484123e-05, "loss": 0.3867, "step": 678 }, { "epoch": 2.75177304964539, "grad_norm": 0.38460961853036985, "learning_rate": 1.985810450327756e-05, "loss": 0.3981, "step": 679 }, { "epoch": 2.7558257345491386, "grad_norm": 0.39507663814375005, "learning_rate": 1.9801347904520706e-05, "loss": 0.3751, "step": 680 }, { "epoch": 2.7598784194528876, "grad_norm": 0.37860774978681155, "learning_rate": 1.974459290568053e-05, "loss": 0.3808, "step": 681 }, { "epoch": 2.763931104356636, "grad_norm": 0.4113473405513068, "learning_rate": 1.968783996385397e-05, "loss": 0.3736, "step": 682 }, { "epoch": 2.767983789260385, "grad_norm": 0.4435353149534309, "learning_rate": 1.963108953612143e-05, "loss": 0.38, "step": 683 }, { "epoch": 2.7720364741641337, "grad_norm": 0.3861534109094039, "learning_rate": 1.9574342079543056e-05, "loss": 0.3896, "step": 684 }, { "epoch": 2.7760891590678822, "grad_norm": 0.42740880012429777, "learning_rate": 1.9517598051155046e-05, "loss": 0.3691, "step": 685 }, { "epoch": 2.780141843971631, "grad_norm": 0.3623737604637641, "learning_rate": 1.9460857907966025e-05, "loss": 0.3757, "step": 686 }, { "epoch": 2.78419452887538, "grad_norm": 0.39156193949987783, "learning_rate": 1.9404122106953285e-05, "loss": 0.3793, "step": 687 }, { "epoch": 2.7882472137791288, "grad_norm": 0.3932330085246938, "learning_rate": 1.9347391105059176e-05, "loss": 0.3922, "step": 688 }, { "epoch": 2.7922998986828773, "grad_norm": 0.3519508323517644, "learning_rate": 1.92906653591874e-05, "loss": 0.3823, "step": 689 }, { "epoch": 2.7963525835866263, "grad_norm": 0.3767444119709347, "learning_rate": 1.9233945326199295e-05, "loss": 0.3897, "step": 690 }, { "epoch": 2.800405268490375, "grad_norm": 0.3728319282448301, "learning_rate": 1.917723146291022e-05, "loss": 0.3866, "step": 691 }, { "epoch": 2.804457953394124, "grad_norm": 0.4102016109415563, "learning_rate": 1.912052422608584e-05, "loss": 0.3675, "step": 692 }, { "epoch": 2.8085106382978724, "grad_norm": 0.34434306116290503, "learning_rate": 1.9063824072438428e-05, "loss": 0.3557, "step": 693 }, { "epoch": 2.812563323201621, "grad_norm": 0.3902517864929646, "learning_rate": 1.9007131458623246e-05, "loss": 0.3849, "step": 694 }, { "epoch": 2.81661600810537, "grad_norm": 0.36256206010063297, "learning_rate": 1.895044684123479e-05, "loss": 0.3683, "step": 695 }, { "epoch": 2.8206686930091185, "grad_norm": 0.38608133916394377, "learning_rate": 1.8893770676803194e-05, "loss": 0.3926, "step": 696 }, { "epoch": 2.8247213779128675, "grad_norm": 0.35827205733960754, "learning_rate": 1.8837103421790486e-05, "loss": 0.3635, "step": 697 }, { "epoch": 2.828774062816616, "grad_norm": 0.3979637154113055, "learning_rate": 1.8780445532586952e-05, "loss": 0.3878, "step": 698 }, { "epoch": 2.8328267477203646, "grad_norm": 0.3841873789489047, "learning_rate": 1.872379746550743e-05, "loss": 0.346, "step": 699 }, { "epoch": 2.8368794326241136, "grad_norm": 0.3427459638042756, "learning_rate": 1.866715967678769e-05, "loss": 0.3851, "step": 700 }, { "epoch": 2.840932117527862, "grad_norm": 0.3979434521075449, "learning_rate": 1.861053262258067e-05, "loss": 0.3911, "step": 701 }, { "epoch": 2.844984802431611, "grad_norm": 0.37381380420731086, "learning_rate": 1.8553916758952897e-05, "loss": 0.3763, "step": 702 }, { "epoch": 2.8490374873353597, "grad_norm": 0.3793688296777444, "learning_rate": 1.8497312541880735e-05, "loss": 0.362, "step": 703 }, { "epoch": 2.853090172239108, "grad_norm": 0.3674791219662531, "learning_rate": 1.8440720427246786e-05, "loss": 0.3833, "step": 704 }, { "epoch": 2.857142857142857, "grad_norm": 0.38145437770490875, "learning_rate": 1.8384140870836157e-05, "loss": 0.3714, "step": 705 }, { "epoch": 2.8611955420466058, "grad_norm": 0.35213060021048614, "learning_rate": 1.8327574328332806e-05, "loss": 0.3569, "step": 706 }, { "epoch": 2.8652482269503547, "grad_norm": 0.34949433069776786, "learning_rate": 1.8271021255315906e-05, "loss": 0.3664, "step": 707 }, { "epoch": 2.8693009118541033, "grad_norm": 0.3709009949572628, "learning_rate": 1.8214482107256117e-05, "loss": 0.3799, "step": 708 }, { "epoch": 2.873353596757852, "grad_norm": 0.37066440498453446, "learning_rate": 1.8157957339511968e-05, "loss": 0.3911, "step": 709 }, { "epoch": 2.877406281661601, "grad_norm": 0.3523618265711624, "learning_rate": 1.8101447407326182e-05, "loss": 0.3761, "step": 710 }, { "epoch": 2.8814589665653494, "grad_norm": 0.38747940968963557, "learning_rate": 1.8044952765821966e-05, "loss": 0.3939, "step": 711 }, { "epoch": 2.8855116514690984, "grad_norm": 0.37472074964057683, "learning_rate": 1.7988473869999407e-05, "loss": 0.3681, "step": 712 }, { "epoch": 2.889564336372847, "grad_norm": 0.38440420798382996, "learning_rate": 1.7932011174731764e-05, "loss": 0.3797, "step": 713 }, { "epoch": 2.8936170212765955, "grad_norm": 0.363196702994756, "learning_rate": 1.7875565134761817e-05, "loss": 0.3714, "step": 714 }, { "epoch": 2.8976697061803445, "grad_norm": 0.3680210862226706, "learning_rate": 1.7819136204698226e-05, "loss": 0.3756, "step": 715 }, { "epoch": 2.9017223910840935, "grad_norm": 0.3819471211574995, "learning_rate": 1.776272483901182e-05, "loss": 0.3709, "step": 716 }, { "epoch": 2.905775075987842, "grad_norm": 0.39754352225387185, "learning_rate": 1.7706331492031995e-05, "loss": 0.3685, "step": 717 }, { "epoch": 2.9098277608915906, "grad_norm": 0.38795236506454567, "learning_rate": 1.764995661794301e-05, "loss": 0.3768, "step": 718 }, { "epoch": 2.9138804457953396, "grad_norm": 0.37447055734407164, "learning_rate": 1.759360067078035e-05, "loss": 0.3896, "step": 719 }, { "epoch": 2.917933130699088, "grad_norm": 0.3659105336937824, "learning_rate": 1.7537264104427064e-05, "loss": 0.3777, "step": 720 }, { "epoch": 2.921985815602837, "grad_norm": 0.35532016905847696, "learning_rate": 1.748094737261012e-05, "loss": 0.3906, "step": 721 }, { "epoch": 2.9260385005065856, "grad_norm": 0.36426913389764304, "learning_rate": 1.7424650928896726e-05, "loss": 0.3558, "step": 722 }, { "epoch": 2.930091185410334, "grad_norm": 0.3390834994043332, "learning_rate": 1.7368375226690712e-05, "loss": 0.3826, "step": 723 }, { "epoch": 2.934143870314083, "grad_norm": 0.38006247429583906, "learning_rate": 1.731212071922883e-05, "loss": 0.3499, "step": 724 }, { "epoch": 2.9381965552178317, "grad_norm": 0.3766950364739606, "learning_rate": 1.7255887859577156e-05, "loss": 0.3925, "step": 725 }, { "epoch": 2.9422492401215807, "grad_norm": 0.3445079726843259, "learning_rate": 1.7199677100627427e-05, "loss": 0.3907, "step": 726 }, { "epoch": 2.9463019250253293, "grad_norm": 0.36767398913176497, "learning_rate": 1.7143488895093343e-05, "loss": 0.3748, "step": 727 }, { "epoch": 2.950354609929078, "grad_norm": 0.36334071602063733, "learning_rate": 1.7087323695506994e-05, "loss": 0.3741, "step": 728 }, { "epoch": 2.954407294832827, "grad_norm": 0.3892231746309117, "learning_rate": 1.7031181954215194e-05, "loss": 0.4068, "step": 729 }, { "epoch": 2.9584599797365754, "grad_norm": 0.3744068704518135, "learning_rate": 1.6975064123375788e-05, "loss": 0.4008, "step": 730 }, { "epoch": 2.9625126646403244, "grad_norm": 0.3527052208533122, "learning_rate": 1.6918970654954084e-05, "loss": 0.3608, "step": 731 }, { "epoch": 2.966565349544073, "grad_norm": 0.34705247102719267, "learning_rate": 1.686290200071915e-05, "loss": 0.3741, "step": 732 }, { "epoch": 2.9706180344478215, "grad_norm": 0.3845768916189244, "learning_rate": 1.6806858612240234e-05, "loss": 0.4008, "step": 733 }, { "epoch": 2.9746707193515705, "grad_norm": 0.36047998183341096, "learning_rate": 1.6750840940883078e-05, "loss": 0.3808, "step": 734 }, { "epoch": 2.978723404255319, "grad_norm": 0.3763867679524316, "learning_rate": 1.6694849437806305e-05, "loss": 0.3693, "step": 735 }, { "epoch": 2.982776089159068, "grad_norm": 0.36441098288125223, "learning_rate": 1.663888455395778e-05, "loss": 0.3759, "step": 736 }, { "epoch": 2.9868287740628165, "grad_norm": 0.3738055776817942, "learning_rate": 1.6582946740070995e-05, "loss": 0.3743, "step": 737 }, { "epoch": 2.990881458966565, "grad_norm": 0.3729511595660726, "learning_rate": 1.6527036446661396e-05, "loss": 0.3845, "step": 738 }, { "epoch": 2.994934143870314, "grad_norm": 0.35001643981401726, "learning_rate": 1.6471154124022818e-05, "loss": 0.3615, "step": 739 }, { "epoch": 2.998986828774063, "grad_norm": 0.3421336303521715, "learning_rate": 1.6415300222223788e-05, "loss": 0.3693, "step": 740 }, { "epoch": 3.0030395136778116, "grad_norm": 0.5600529519261276, "learning_rate": 1.6359475191103958e-05, "loss": 0.2899, "step": 741 }, { "epoch": 3.00709219858156, "grad_norm": 0.40062655237685113, "learning_rate": 1.6303679480270466e-05, "loss": 0.2639, "step": 742 }, { "epoch": 3.011144883485309, "grad_norm": 0.4904935328441184, "learning_rate": 1.624791353909428e-05, "loss": 0.2666, "step": 743 }, { "epoch": 3.0151975683890577, "grad_norm": 0.7119800692226997, "learning_rate": 1.619217781670663e-05, "loss": 0.265, "step": 744 }, { "epoch": 3.0192502532928063, "grad_norm": 0.42404178935688747, "learning_rate": 1.6136472761995373e-05, "loss": 0.2757, "step": 745 }, { "epoch": 3.0233029381965553, "grad_norm": 0.5232870554733102, "learning_rate": 1.608079882360134e-05, "loss": 0.2551, "step": 746 }, { "epoch": 3.027355623100304, "grad_norm": 0.4974571537460195, "learning_rate": 1.60251564499148e-05, "loss": 0.2813, "step": 747 }, { "epoch": 3.031408308004053, "grad_norm": 0.3708092464792635, "learning_rate": 1.596954608907176e-05, "loss": 0.2639, "step": 748 }, { "epoch": 3.0354609929078014, "grad_norm": 0.47499905270420256, "learning_rate": 1.591396818895043e-05, "loss": 0.2779, "step": 749 }, { "epoch": 3.0395136778115504, "grad_norm": 0.43463722378980485, "learning_rate": 1.585842319716759e-05, "loss": 0.2715, "step": 750 }, { "epoch": 3.043566362715299, "grad_norm": 0.3929820249092284, "learning_rate": 1.5802911561074944e-05, "loss": 0.2575, "step": 751 }, { "epoch": 3.0476190476190474, "grad_norm": 0.40298032506059567, "learning_rate": 1.5747433727755595e-05, "loss": 0.2468, "step": 752 }, { "epoch": 3.0516717325227964, "grad_norm": 0.3795494101135109, "learning_rate": 1.5691990144020376e-05, "loss": 0.262, "step": 753 }, { "epoch": 3.055724417426545, "grad_norm": 0.43527058986853423, "learning_rate": 1.5636581256404297e-05, "loss": 0.2493, "step": 754 }, { "epoch": 3.059777102330294, "grad_norm": 0.38366039855973616, "learning_rate": 1.558120751116291e-05, "loss": 0.2499, "step": 755 }, { "epoch": 3.0638297872340425, "grad_norm": 0.3703456193450308, "learning_rate": 1.552586935426876e-05, "loss": 0.259, "step": 756 }, { "epoch": 3.067882472137791, "grad_norm": 0.38926982776480284, "learning_rate": 1.547056723140774e-05, "loss": 0.2686, "step": 757 }, { "epoch": 3.07193515704154, "grad_norm": 0.3971691022782858, "learning_rate": 1.5415301587975565e-05, "loss": 0.274, "step": 758 }, { "epoch": 3.0759878419452886, "grad_norm": 0.34259308049622955, "learning_rate": 1.536007286907411e-05, "loss": 0.2785, "step": 759 }, { "epoch": 3.0800405268490376, "grad_norm": 0.3519055701287284, "learning_rate": 1.5304881519507896e-05, "loss": 0.2685, "step": 760 }, { "epoch": 3.084093211752786, "grad_norm": 0.3986279325917256, "learning_rate": 1.5249727983780453e-05, "loss": 0.2671, "step": 761 }, { "epoch": 3.088145896656535, "grad_norm": 0.33498139064686766, "learning_rate": 1.5194612706090786e-05, "loss": 0.2604, "step": 762 }, { "epoch": 3.0921985815602837, "grad_norm": 0.35506082326468474, "learning_rate": 1.5139536130329771e-05, "loss": 0.2781, "step": 763 }, { "epoch": 3.0962512664640323, "grad_norm": 0.37338973342339954, "learning_rate": 1.508449870007656e-05, "loss": 0.276, "step": 764 }, { "epoch": 3.1003039513677813, "grad_norm": 0.35216263535692055, "learning_rate": 1.5029500858595056e-05, "loss": 0.2752, "step": 765 }, { "epoch": 3.10435663627153, "grad_norm": 0.379257491254358, "learning_rate": 1.4974543048830328e-05, "loss": 0.2728, "step": 766 }, { "epoch": 3.108409321175279, "grad_norm": 0.34727114309387874, "learning_rate": 1.4919625713405e-05, "loss": 0.2642, "step": 767 }, { "epoch": 3.1124620060790273, "grad_norm": 0.34699442460768515, "learning_rate": 1.4864749294615756e-05, "loss": 0.2425, "step": 768 }, { "epoch": 3.116514690982776, "grad_norm": 0.32785053229340233, "learning_rate": 1.4809914234429716e-05, "loss": 0.2658, "step": 769 }, { "epoch": 3.120567375886525, "grad_norm": 0.33378848976125164, "learning_rate": 1.4755120974480923e-05, "loss": 0.2738, "step": 770 }, { "epoch": 3.1246200607902734, "grad_norm": 0.3218517747604464, "learning_rate": 1.4700369956066771e-05, "loss": 0.2364, "step": 771 }, { "epoch": 3.1286727456940224, "grad_norm": 0.3508861737946556, "learning_rate": 1.4645661620144413e-05, "loss": 0.2621, "step": 772 }, { "epoch": 3.132725430597771, "grad_norm": 0.3278541522766288, "learning_rate": 1.4590996407327284e-05, "loss": 0.2533, "step": 773 }, { "epoch": 3.13677811550152, "grad_norm": 0.34665588248462076, "learning_rate": 1.4536374757881487e-05, "loss": 0.2903, "step": 774 }, { "epoch": 3.1408308004052685, "grad_norm": 0.3341243227978257, "learning_rate": 1.4481797111722271e-05, "loss": 0.2604, "step": 775 }, { "epoch": 3.144883485309017, "grad_norm": 0.32195920903254105, "learning_rate": 1.4427263908410507e-05, "loss": 0.2691, "step": 776 }, { "epoch": 3.148936170212766, "grad_norm": 0.3344948074415684, "learning_rate": 1.4372775587149108e-05, "loss": 0.2799, "step": 777 }, { "epoch": 3.1529888551165146, "grad_norm": 0.3211184436106537, "learning_rate": 1.4318332586779522e-05, "loss": 0.2691, "step": 778 }, { "epoch": 3.1570415400202636, "grad_norm": 0.336496421450049, "learning_rate": 1.4263935345778202e-05, "loss": 0.2547, "step": 779 }, { "epoch": 3.161094224924012, "grad_norm": 0.3320265683727049, "learning_rate": 1.420958430225303e-05, "loss": 0.2649, "step": 780 }, { "epoch": 3.1651469098277607, "grad_norm": 0.3147161518900082, "learning_rate": 1.415527989393985e-05, "loss": 0.2811, "step": 781 }, { "epoch": 3.1691995947315097, "grad_norm": 0.33554847626065776, "learning_rate": 1.410102255819891e-05, "loss": 0.2755, "step": 782 }, { "epoch": 3.1732522796352582, "grad_norm": 0.3219281622858217, "learning_rate": 1.404681273201131e-05, "loss": 0.257, "step": 783 }, { "epoch": 3.1773049645390072, "grad_norm": 0.3307754836566679, "learning_rate": 1.399265085197556e-05, "loss": 0.2525, "step": 784 }, { "epoch": 3.181357649442756, "grad_norm": 0.3368758051951691, "learning_rate": 1.393853735430398e-05, "loss": 0.2704, "step": 785 }, { "epoch": 3.1854103343465043, "grad_norm": 0.3545040034181631, "learning_rate": 1.3884472674819246e-05, "loss": 0.2599, "step": 786 }, { "epoch": 3.1894630192502533, "grad_norm": 0.3387686816478282, "learning_rate": 1.3830457248950864e-05, "loss": 0.261, "step": 787 }, { "epoch": 3.193515704154002, "grad_norm": 0.6260775634296268, "learning_rate": 1.377649151173163e-05, "loss": 0.2676, "step": 788 }, { "epoch": 3.197568389057751, "grad_norm": 0.34774391051268577, "learning_rate": 1.3722575897794181e-05, "loss": 0.2649, "step": 789 }, { "epoch": 3.2016210739614994, "grad_norm": 0.3200340078719376, "learning_rate": 1.3668710841367472e-05, "loss": 0.2646, "step": 790 }, { "epoch": 3.2056737588652484, "grad_norm": 0.33712219582514896, "learning_rate": 1.361489677627324e-05, "loss": 0.2702, "step": 791 }, { "epoch": 3.209726443768997, "grad_norm": 0.34090566307362863, "learning_rate": 1.3561134135922585e-05, "loss": 0.2577, "step": 792 }, { "epoch": 3.2137791286727455, "grad_norm": 0.34090994377651584, "learning_rate": 1.350742335331241e-05, "loss": 0.2739, "step": 793 }, { "epoch": 3.2178318135764945, "grad_norm": 0.32758417576795545, "learning_rate": 1.345376486102198e-05, "loss": 0.2365, "step": 794 }, { "epoch": 3.221884498480243, "grad_norm": 0.31947044505856886, "learning_rate": 1.3400159091209414e-05, "loss": 0.2872, "step": 795 }, { "epoch": 3.225937183383992, "grad_norm": 0.3460900206595306, "learning_rate": 1.3346606475608216e-05, "loss": 0.2528, "step": 796 }, { "epoch": 3.2299898682877406, "grad_norm": 0.3210062034818833, "learning_rate": 1.3293107445523781e-05, "loss": 0.2736, "step": 797 }, { "epoch": 3.2340425531914896, "grad_norm": 0.32619214077310826, "learning_rate": 1.3239662431829949e-05, "loss": 0.2599, "step": 798 }, { "epoch": 3.238095238095238, "grad_norm": 0.3359157797286736, "learning_rate": 1.3186271864965509e-05, "loss": 0.2586, "step": 799 }, { "epoch": 3.2421479229989867, "grad_norm": 0.30941949941469704, "learning_rate": 1.3132936174930756e-05, "loss": 0.2785, "step": 800 }, { "epoch": 3.2462006079027357, "grad_norm": 0.3229983694924969, "learning_rate": 1.3079655791283995e-05, "loss": 0.2586, "step": 801 }, { "epoch": 3.2502532928064842, "grad_norm": 0.33128953406197204, "learning_rate": 1.3026431143138108e-05, "loss": 0.2868, "step": 802 }, { "epoch": 3.254305977710233, "grad_norm": 0.3321507795647326, "learning_rate": 1.2973262659157114e-05, "loss": 0.2658, "step": 803 }, { "epoch": 3.2583586626139818, "grad_norm": 0.3315643951898538, "learning_rate": 1.2920150767552651e-05, "loss": 0.2604, "step": 804 }, { "epoch": 3.2624113475177303, "grad_norm": 0.31291061983277974, "learning_rate": 1.2867095896080607e-05, "loss": 0.2604, "step": 805 }, { "epoch": 3.2664640324214793, "grad_norm": 0.3123892787685489, "learning_rate": 1.2814098472037612e-05, "loss": 0.2694, "step": 806 }, { "epoch": 3.270516717325228, "grad_norm": 0.31219030375062823, "learning_rate": 1.276115892225764e-05, "loss": 0.2732, "step": 807 }, { "epoch": 3.274569402228977, "grad_norm": 0.3225341656832403, "learning_rate": 1.2708277673108555e-05, "loss": 0.2536, "step": 808 }, { "epoch": 3.2786220871327254, "grad_norm": 0.3236606895721125, "learning_rate": 1.2655455150488649e-05, "loss": 0.2684, "step": 809 }, { "epoch": 3.282674772036474, "grad_norm": 0.3345680849985815, "learning_rate": 1.2602691779823272e-05, "loss": 0.2501, "step": 810 }, { "epoch": 3.286727456940223, "grad_norm": 0.3170114262475946, "learning_rate": 1.2549987986061355e-05, "loss": 0.2615, "step": 811 }, { "epoch": 3.2907801418439715, "grad_norm": 0.2977160931511391, "learning_rate": 1.2497344193672005e-05, "loss": 0.2716, "step": 812 }, { "epoch": 3.2948328267477205, "grad_norm": 0.31474378973195855, "learning_rate": 1.2444760826641092e-05, "loss": 0.2626, "step": 813 }, { "epoch": 3.298885511651469, "grad_norm": 0.3148636434779564, "learning_rate": 1.2392238308467817e-05, "loss": 0.2498, "step": 814 }, { "epoch": 3.3029381965552176, "grad_norm": 0.3211908279459109, "learning_rate": 1.2339777062161326e-05, "loss": 0.2636, "step": 815 }, { "epoch": 3.3069908814589666, "grad_norm": 0.3144857442262971, "learning_rate": 1.2287377510237293e-05, "loss": 0.2684, "step": 816 }, { "epoch": 3.311043566362715, "grad_norm": 0.332194708455874, "learning_rate": 1.2235040074714488e-05, "loss": 0.2353, "step": 817 }, { "epoch": 3.315096251266464, "grad_norm": 0.3151369336504755, "learning_rate": 1.2182765177111434e-05, "loss": 0.2588, "step": 818 }, { "epoch": 3.3191489361702127, "grad_norm": 0.30660696690316586, "learning_rate": 1.213055323844297e-05, "loss": 0.2545, "step": 819 }, { "epoch": 3.3232016210739617, "grad_norm": 0.3194962613887905, "learning_rate": 1.2078404679216864e-05, "loss": 0.2621, "step": 820 }, { "epoch": 3.32725430597771, "grad_norm": 0.32662331541891854, "learning_rate": 1.2026319919430458e-05, "loss": 0.2705, "step": 821 }, { "epoch": 3.331306990881459, "grad_norm": 0.31676091474994, "learning_rate": 1.1974299378567227e-05, "loss": 0.2577, "step": 822 }, { "epoch": 3.3353596757852078, "grad_norm": 0.321280032927269, "learning_rate": 1.1922343475593462e-05, "loss": 0.267, "step": 823 }, { "epoch": 3.3394123606889563, "grad_norm": 0.29663169391790173, "learning_rate": 1.187045262895488e-05, "loss": 0.2503, "step": 824 }, { "epoch": 3.3434650455927053, "grad_norm": 0.3132011003523163, "learning_rate": 1.1818627256573203e-05, "loss": 0.2631, "step": 825 }, { "epoch": 3.347517730496454, "grad_norm": 0.35902221639637133, "learning_rate": 1.1766867775842864e-05, "loss": 0.2483, "step": 826 }, { "epoch": 3.351570415400203, "grad_norm": 0.3207823786103355, "learning_rate": 1.1715174603627615e-05, "loss": 0.2694, "step": 827 }, { "epoch": 3.3556231003039514, "grad_norm": 0.32494475598976197, "learning_rate": 1.1663548156257147e-05, "loss": 0.2778, "step": 828 }, { "epoch": 3.3596757852077, "grad_norm": 0.35534253997490584, "learning_rate": 1.161198884952377e-05, "loss": 0.2778, "step": 829 }, { "epoch": 3.363728470111449, "grad_norm": 0.31771795045997614, "learning_rate": 1.1560497098679056e-05, "loss": 0.2955, "step": 830 }, { "epoch": 3.3677811550151975, "grad_norm": 0.3254710910459406, "learning_rate": 1.1509073318430479e-05, "loss": 0.2724, "step": 831 }, { "epoch": 3.3718338399189465, "grad_norm": 0.32610464930335553, "learning_rate": 1.1457717922938116e-05, "loss": 0.2572, "step": 832 }, { "epoch": 3.375886524822695, "grad_norm": 0.32016536013857216, "learning_rate": 1.1406431325811233e-05, "loss": 0.2851, "step": 833 }, { "epoch": 3.3799392097264436, "grad_norm": 0.32613824085952187, "learning_rate": 1.135521394010506e-05, "loss": 0.269, "step": 834 }, { "epoch": 3.3839918946301926, "grad_norm": 0.3176061729200933, "learning_rate": 1.1304066178317367e-05, "loss": 0.2678, "step": 835 }, { "epoch": 3.388044579533941, "grad_norm": 0.3273414850683646, "learning_rate": 1.1252988452385199e-05, "loss": 0.2667, "step": 836 }, { "epoch": 3.39209726443769, "grad_norm": 0.3143731753866215, "learning_rate": 1.1201981173681536e-05, "loss": 0.2646, "step": 837 }, { "epoch": 3.3961499493414387, "grad_norm": 0.3247811205827489, "learning_rate": 1.1151044753011991e-05, "loss": 0.2619, "step": 838 }, { "epoch": 3.400202634245187, "grad_norm": 1.8947263124000093, "learning_rate": 1.1100179600611491e-05, "loss": 0.2713, "step": 839 }, { "epoch": 3.404255319148936, "grad_norm": 0.33637947850863703, "learning_rate": 1.1049386126140985e-05, "loss": 0.2602, "step": 840 }, { "epoch": 3.4083080040526847, "grad_norm": 0.3150752281938797, "learning_rate": 1.0998664738684128e-05, "loss": 0.2854, "step": 841 }, { "epoch": 3.4123606889564337, "grad_norm": 0.3347151860197323, "learning_rate": 1.0948015846744e-05, "loss": 0.2474, "step": 842 }, { "epoch": 3.4164133738601823, "grad_norm": 0.511450944906848, "learning_rate": 1.0897439858239832e-05, "loss": 0.2713, "step": 843 }, { "epoch": 3.4204660587639313, "grad_norm": 0.41419552933404846, "learning_rate": 1.0846937180503652e-05, "loss": 0.2689, "step": 844 }, { "epoch": 3.42451874366768, "grad_norm": 0.3285347976746443, "learning_rate": 1.0796508220277117e-05, "loss": 0.2464, "step": 845 }, { "epoch": 3.4285714285714284, "grad_norm": 0.3083169453724999, "learning_rate": 1.0746153383708107e-05, "loss": 0.2532, "step": 846 }, { "epoch": 3.4326241134751774, "grad_norm": 0.31245259800402425, "learning_rate": 1.0695873076347579e-05, "loss": 0.2846, "step": 847 }, { "epoch": 3.436676798378926, "grad_norm": 0.3032968702113556, "learning_rate": 1.0645667703146205e-05, "loss": 0.2708, "step": 848 }, { "epoch": 3.440729483282675, "grad_norm": 0.3224705636965893, "learning_rate": 1.0595537668451161e-05, "loss": 0.2596, "step": 849 }, { "epoch": 3.4447821681864235, "grad_norm": 0.32835399980698077, "learning_rate": 1.0545483376002854e-05, "loss": 0.2932, "step": 850 }, { "epoch": 3.4488348530901725, "grad_norm": 0.31332341150486, "learning_rate": 1.0495505228931676e-05, "loss": 0.289, "step": 851 }, { "epoch": 3.452887537993921, "grad_norm": 0.30600721413225457, "learning_rate": 1.044560362975474e-05, "loss": 0.2744, "step": 852 }, { "epoch": 3.4569402228976696, "grad_norm": 0.31285740494514, "learning_rate": 1.0395778980372695e-05, "loss": 0.2532, "step": 853 }, { "epoch": 3.4609929078014185, "grad_norm": 0.30720270954326273, "learning_rate": 1.0346031682066381e-05, "loss": 0.2742, "step": 854 }, { "epoch": 3.465045592705167, "grad_norm": 0.3089313609771571, "learning_rate": 1.0296362135493724e-05, "loss": 0.257, "step": 855 }, { "epoch": 3.469098277608916, "grad_norm": 0.29999508361374144, "learning_rate": 1.0246770740686422e-05, "loss": 0.2771, "step": 856 }, { "epoch": 3.4731509625126646, "grad_norm": 0.3068670286580572, "learning_rate": 1.0197257897046743e-05, "loss": 0.252, "step": 857 }, { "epoch": 3.477203647416413, "grad_norm": 0.3058522340242042, "learning_rate": 1.014782400334433e-05, "loss": 0.2571, "step": 858 }, { "epoch": 3.481256332320162, "grad_norm": 0.29985560401095307, "learning_rate": 1.009846945771296e-05, "loss": 0.2615, "step": 859 }, { "epoch": 3.4853090172239107, "grad_norm": 0.314301350699763, "learning_rate": 1.0049194657647363e-05, "loss": 0.2604, "step": 860 }, { "epoch": 3.4893617021276597, "grad_norm": 0.2925623883163185, "learning_rate": 1.0000000000000006e-05, "loss": 0.261, "step": 861 }, { "epoch": 3.4934143870314083, "grad_norm": 0.3029121847837866, "learning_rate": 9.950885880977891e-06, "loss": 0.2526, "step": 862 }, { "epoch": 3.497467071935157, "grad_norm": 0.3135906596148526, "learning_rate": 9.901852696139382e-06, "loss": 0.2617, "step": 863 }, { "epoch": 3.501519756838906, "grad_norm": 0.3135084579948363, "learning_rate": 9.852900840391027e-06, "loss": 0.263, "step": 864 }, { "epoch": 3.5055724417426544, "grad_norm": 0.3096812555810701, "learning_rate": 9.804030707984313e-06, "loss": 0.2657, "step": 865 }, { "epoch": 3.5096251266464034, "grad_norm": 0.31641953443361814, "learning_rate": 9.755242692512599e-06, "loss": 0.2426, "step": 866 }, { "epoch": 3.513677811550152, "grad_norm": 0.33044668134732463, "learning_rate": 9.70653718690782e-06, "loss": 0.2383, "step": 867 }, { "epoch": 3.5177304964539005, "grad_norm": 0.3165205582220823, "learning_rate": 9.657914583437454e-06, "loss": 0.253, "step": 868 }, { "epoch": 3.5217831813576495, "grad_norm": 0.3307205764242631, "learning_rate": 9.609375273701246e-06, "loss": 0.2708, "step": 869 }, { "epoch": 3.5258358662613984, "grad_norm": 0.3066516033471303, "learning_rate": 9.560919648628133e-06, "loss": 0.2594, "step": 870 }, { "epoch": 3.529888551165147, "grad_norm": 0.3246657963078779, "learning_rate": 9.512548098473047e-06, "loss": 0.2096, "step": 871 }, { "epoch": 3.5339412360688955, "grad_norm": 0.3362957974542694, "learning_rate": 9.464261012813825e-06, "loss": 0.2759, "step": 872 }, { "epoch": 3.5379939209726445, "grad_norm": 0.3304485978677205, "learning_rate": 9.416058780547987e-06, "loss": 0.2898, "step": 873 }, { "epoch": 3.542046605876393, "grad_norm": 0.31133390632645674, "learning_rate": 9.367941789889714e-06, "loss": 0.2752, "step": 874 }, { "epoch": 3.546099290780142, "grad_norm": 0.29849994820716225, "learning_rate": 9.319910428366607e-06, "loss": 0.2912, "step": 875 }, { "epoch": 3.5501519756838906, "grad_norm": 0.3208314249649794, "learning_rate": 9.271965082816667e-06, "loss": 0.2526, "step": 876 }, { "epoch": 3.554204660587639, "grad_norm": 0.32125883300988467, "learning_rate": 9.224106139385111e-06, "loss": 0.266, "step": 877 }, { "epoch": 3.558257345491388, "grad_norm": 0.314356104752064, "learning_rate": 9.176333983521291e-06, "loss": 0.2352, "step": 878 }, { "epoch": 3.5623100303951367, "grad_norm": 0.3389958884059575, "learning_rate": 9.12864899997558e-06, "loss": 0.2776, "step": 879 }, { "epoch": 3.5663627152988857, "grad_norm": 0.3273219643483403, "learning_rate": 9.08105157279628e-06, "loss": 0.274, "step": 880 }, { "epoch": 3.5704154002026343, "grad_norm": 0.32617511078993644, "learning_rate": 9.03354208532653e-06, "loss": 0.2772, "step": 881 }, { "epoch": 3.574468085106383, "grad_norm": 0.3145058960162268, "learning_rate": 8.986120920201205e-06, "loss": 0.261, "step": 882 }, { "epoch": 3.578520770010132, "grad_norm": 0.3077975385039152, "learning_rate": 8.938788459343852e-06, "loss": 0.2701, "step": 883 }, { "epoch": 3.5825734549138804, "grad_norm": 0.312000193748488, "learning_rate": 8.8915450839636e-06, "loss": 0.281, "step": 884 }, { "epoch": 3.5866261398176293, "grad_norm": 0.29972825163373873, "learning_rate": 8.844391174552116e-06, "loss": 0.2554, "step": 885 }, { "epoch": 3.590678824721378, "grad_norm": 0.31132922076152514, "learning_rate": 8.797327110880479e-06, "loss": 0.2662, "step": 886 }, { "epoch": 3.5947315096251264, "grad_norm": 0.3327088625654375, "learning_rate": 8.750353271996206e-06, "loss": 0.2736, "step": 887 }, { "epoch": 3.5987841945288754, "grad_norm": 0.29955418519195676, "learning_rate": 8.703470036220132e-06, "loss": 0.2592, "step": 888 }, { "epoch": 3.602836879432624, "grad_norm": 0.31535405206103595, "learning_rate": 8.656677781143394e-06, "loss": 0.2697, "step": 889 }, { "epoch": 3.606889564336373, "grad_norm": 0.31500185967340805, "learning_rate": 8.609976883624377e-06, "loss": 0.2651, "step": 890 }, { "epoch": 3.6109422492401215, "grad_norm": 0.2959567535285897, "learning_rate": 8.563367719785698e-06, "loss": 0.2584, "step": 891 }, { "epoch": 3.61499493414387, "grad_norm": 0.29971699468290663, "learning_rate": 8.516850665011138e-06, "loss": 0.2778, "step": 892 }, { "epoch": 3.619047619047619, "grad_norm": 0.2987705236125032, "learning_rate": 8.47042609394269e-06, "loss": 0.2522, "step": 893 }, { "epoch": 3.6231003039513676, "grad_norm": 0.2965735003444721, "learning_rate": 8.424094380477432e-06, "loss": 0.2614, "step": 894 }, { "epoch": 3.6271529888551166, "grad_norm": 0.3197425604522645, "learning_rate": 8.37785589776465e-06, "loss": 0.2851, "step": 895 }, { "epoch": 3.631205673758865, "grad_norm": 0.30693228647403803, "learning_rate": 8.331711018202694e-06, "loss": 0.2822, "step": 896 }, { "epoch": 3.6352583586626137, "grad_norm": 0.3133813075925239, "learning_rate": 8.285660113436104e-06, "loss": 0.2558, "step": 897 }, { "epoch": 3.6393110435663627, "grad_norm": 0.31166912098127175, "learning_rate": 8.239703554352527e-06, "loss": 0.2817, "step": 898 }, { "epoch": 3.6433637284701117, "grad_norm": 0.2960859122048135, "learning_rate": 8.193841711079775e-06, "loss": 0.2627, "step": 899 }, { "epoch": 3.6474164133738602, "grad_norm": 0.30366440571292913, "learning_rate": 8.148074952982828e-06, "loss": 0.2439, "step": 900 }, { "epoch": 3.651469098277609, "grad_norm": 0.3091690452424721, "learning_rate": 8.102403648660859e-06, "loss": 0.2659, "step": 901 }, { "epoch": 3.655521783181358, "grad_norm": 0.315231891692595, "learning_rate": 8.056828165944282e-06, "loss": 0.2516, "step": 902 }, { "epoch": 3.6595744680851063, "grad_norm": 0.3215566760445528, "learning_rate": 8.011348871891762e-06, "loss": 0.2734, "step": 903 }, { "epoch": 3.6636271529888553, "grad_norm": 0.3304114603125728, "learning_rate": 7.965966132787287e-06, "loss": 0.2788, "step": 904 }, { "epoch": 3.667679837892604, "grad_norm": 0.31294537288978014, "learning_rate": 7.920680314137189e-06, "loss": 0.2667, "step": 905 }, { "epoch": 3.6717325227963524, "grad_norm": 0.3137553525432779, "learning_rate": 7.875491780667246e-06, "loss": 0.2473, "step": 906 }, { "epoch": 3.6757852077001014, "grad_norm": 0.3169350317800105, "learning_rate": 7.830400896319667e-06, "loss": 0.2751, "step": 907 }, { "epoch": 3.67983789260385, "grad_norm": 0.32899558223738445, "learning_rate": 7.785408024250259e-06, "loss": 0.2455, "step": 908 }, { "epoch": 3.683890577507599, "grad_norm": 0.3008678539357601, "learning_rate": 7.74051352682542e-06, "loss": 0.2541, "step": 909 }, { "epoch": 3.6879432624113475, "grad_norm": 0.3182914366084159, "learning_rate": 7.695717765619257e-06, "loss": 0.2676, "step": 910 }, { "epoch": 3.691995947315096, "grad_norm": 0.3151022840055354, "learning_rate": 7.651021101410673e-06, "loss": 0.2491, "step": 911 }, { "epoch": 3.696048632218845, "grad_norm": 0.3176289420458808, "learning_rate": 7.606423894180464e-06, "loss": 0.2385, "step": 912 }, { "epoch": 3.7001013171225936, "grad_norm": 0.3119660430144287, "learning_rate": 7.56192650310839e-06, "loss": 0.2652, "step": 913 }, { "epoch": 3.7041540020263426, "grad_norm": 0.31763258325249577, "learning_rate": 7.517529286570349e-06, "loss": 0.2549, "step": 914 }, { "epoch": 3.708206686930091, "grad_norm": 0.30881313545233424, "learning_rate": 7.473232602135387e-06, "loss": 0.2518, "step": 915 }, { "epoch": 3.7122593718338397, "grad_norm": 0.30385436324208165, "learning_rate": 7.429036806562935e-06, "loss": 0.2449, "step": 916 }, { "epoch": 3.7163120567375887, "grad_norm": 0.30982099077160963, "learning_rate": 7.3849422557998455e-06, "loss": 0.2488, "step": 917 }, { "epoch": 3.7203647416413372, "grad_norm": 0.3172414755307915, "learning_rate": 7.340949304977567e-06, "loss": 0.2604, "step": 918 }, { "epoch": 3.7244174265450862, "grad_norm": 0.3298378403525879, "learning_rate": 7.297058308409282e-06, "loss": 0.2557, "step": 919 }, { "epoch": 3.728470111448835, "grad_norm": 0.31675431972545304, "learning_rate": 7.25326961958704e-06, "loss": 0.2628, "step": 920 }, { "epoch": 3.7325227963525833, "grad_norm": 0.32183988345521586, "learning_rate": 7.209583591178921e-06, "loss": 0.2701, "step": 921 }, { "epoch": 3.7365754812563323, "grad_norm": 0.30879046650738046, "learning_rate": 7.1660005750261925e-06, "loss": 0.2646, "step": 922 }, { "epoch": 3.7406281661600813, "grad_norm": 0.3216410098313188, "learning_rate": 7.1225209221404765e-06, "loss": 0.254, "step": 923 }, { "epoch": 3.74468085106383, "grad_norm": 0.3145039362722645, "learning_rate": 7.079144982700909e-06, "loss": 0.263, "step": 924 }, { "epoch": 3.7487335359675784, "grad_norm": 0.29437008791437835, "learning_rate": 7.0358731060513695e-06, "loss": 0.2479, "step": 925 }, { "epoch": 3.7527862208713274, "grad_norm": 0.3044342051730224, "learning_rate": 6.99270564069757e-06, "loss": 0.2557, "step": 926 }, { "epoch": 3.756838905775076, "grad_norm": 0.3024636673356088, "learning_rate": 6.949642934304375e-06, "loss": 0.2688, "step": 927 }, { "epoch": 3.760891590678825, "grad_norm": 0.29203716284985315, "learning_rate": 6.906685333692871e-06, "loss": 0.2603, "step": 928 }, { "epoch": 3.7649442755825735, "grad_norm": 0.30152363046942754, "learning_rate": 6.86383318483769e-06, "loss": 0.2774, "step": 929 }, { "epoch": 3.768996960486322, "grad_norm": 0.29801377764970816, "learning_rate": 6.821086832864139e-06, "loss": 0.2532, "step": 930 }, { "epoch": 3.773049645390071, "grad_norm": 0.29839047371386357, "learning_rate": 6.77844662204546e-06, "loss": 0.2796, "step": 931 }, { "epoch": 3.7771023302938196, "grad_norm": 0.31535956964117756, "learning_rate": 6.7359128958000455e-06, "loss": 0.2577, "step": 932 }, { "epoch": 3.7811550151975686, "grad_norm": 0.31044301065692237, "learning_rate": 6.693485996688695e-06, "loss": 0.2644, "step": 933 }, { "epoch": 3.785207700101317, "grad_norm": 0.29548251048550833, "learning_rate": 6.651166266411801e-06, "loss": 0.2658, "step": 934 }, { "epoch": 3.7892603850050657, "grad_norm": 0.3067785826909148, "learning_rate": 6.6089540458066725e-06, "loss": 0.2671, "step": 935 }, { "epoch": 3.7933130699088147, "grad_norm": 0.3066620985068279, "learning_rate": 6.566849674844711e-06, "loss": 0.265, "step": 936 }, { "epoch": 3.797365754812563, "grad_norm": 0.32209579521116294, "learning_rate": 6.524853492628747e-06, "loss": 0.2502, "step": 937 }, { "epoch": 3.801418439716312, "grad_norm": 0.29942548070936587, "learning_rate": 6.4829658373902536e-06, "loss": 0.2801, "step": 938 }, { "epoch": 3.8054711246200608, "grad_norm": 0.293065519953897, "learning_rate": 6.441187046486648e-06, "loss": 0.2481, "step": 939 }, { "epoch": 3.8095238095238093, "grad_norm": 0.29049131298288855, "learning_rate": 6.399517456398567e-06, "loss": 0.2602, "step": 940 }, { "epoch": 3.8135764944275583, "grad_norm": 0.30369176668732883, "learning_rate": 6.357957402727164e-06, "loss": 0.2635, "step": 941 }, { "epoch": 3.817629179331307, "grad_norm": 0.3067513510029192, "learning_rate": 6.316507220191395e-06, "loss": 0.2635, "step": 942 }, { "epoch": 3.821681864235056, "grad_norm": 0.3194165398819077, "learning_rate": 6.275167242625331e-06, "loss": 0.2487, "step": 943 }, { "epoch": 3.8257345491388044, "grad_norm": 0.30171946107430697, "learning_rate": 6.233937802975471e-06, "loss": 0.2444, "step": 944 }, { "epoch": 3.829787234042553, "grad_norm": 0.30196780788185257, "learning_rate": 6.192819233298046e-06, "loss": 0.2756, "step": 945 }, { "epoch": 3.833839918946302, "grad_norm": 0.3086260115771585, "learning_rate": 6.151811864756383e-06, "loss": 0.2666, "step": 946 }, { "epoch": 3.837892603850051, "grad_norm": 0.30998694081313144, "learning_rate": 6.1109160276181655e-06, "loss": 0.2599, "step": 947 }, { "epoch": 3.8419452887537995, "grad_norm": 0.28273260444463266, "learning_rate": 6.070132051252868e-06, "loss": 0.2879, "step": 948 }, { "epoch": 3.845997973657548, "grad_norm": 0.29542376626541444, "learning_rate": 6.0294602641290034e-06, "loss": 0.2525, "step": 949 }, { "epoch": 3.850050658561297, "grad_norm": 0.31605097595317233, "learning_rate": 5.988900993811575e-06, "loss": 0.2538, "step": 950 }, { "epoch": 3.8541033434650456, "grad_norm": 0.30016612154804717, "learning_rate": 5.948454566959363e-06, "loss": 0.2611, "step": 951 }, { "epoch": 3.8581560283687946, "grad_norm": 0.3010782584811012, "learning_rate": 5.908121309322328e-06, "loss": 0.2906, "step": 952 }, { "epoch": 3.862208713272543, "grad_norm": 0.2941824997238047, "learning_rate": 5.867901545738976e-06, "loss": 0.2292, "step": 953 }, { "epoch": 3.8662613981762917, "grad_norm": 0.3004609017328805, "learning_rate": 5.827795600133774e-06, "loss": 0.2464, "step": 954 }, { "epoch": 3.8703140830800407, "grad_norm": 0.30811035529085995, "learning_rate": 5.787803795514466e-06, "loss": 0.24, "step": 955 }, { "epoch": 3.874366767983789, "grad_norm": 0.3055434035747132, "learning_rate": 5.747926453969576e-06, "loss": 0.2606, "step": 956 }, { "epoch": 3.878419452887538, "grad_norm": 0.2916824121672623, "learning_rate": 5.708163896665708e-06, "loss": 0.2868, "step": 957 }, { "epoch": 3.8824721377912867, "grad_norm": 0.2903844656847278, "learning_rate": 5.668516443845047e-06, "loss": 0.2613, "step": 958 }, { "epoch": 3.8865248226950353, "grad_norm": 0.2950092733275902, "learning_rate": 5.6289844148227225e-06, "loss": 0.2701, "step": 959 }, { "epoch": 3.8905775075987843, "grad_norm": 0.3188163619027849, "learning_rate": 5.5895681279842615e-06, "loss": 0.267, "step": 960 }, { "epoch": 3.894630192502533, "grad_norm": 0.29002937516427496, "learning_rate": 5.550267900783019e-06, "loss": 0.2583, "step": 961 }, { "epoch": 3.898682877406282, "grad_norm": 0.2957613648308718, "learning_rate": 5.511084049737623e-06, "loss": 0.239, "step": 962 }, { "epoch": 3.9027355623100304, "grad_norm": 0.3078390964841555, "learning_rate": 5.4720168904294215e-06, "loss": 0.2719, "step": 963 }, { "epoch": 3.906788247213779, "grad_norm": 0.28757271285603414, "learning_rate": 5.433066737499948e-06, "loss": 0.2483, "step": 964 }, { "epoch": 3.910840932117528, "grad_norm": 0.2898065513805054, "learning_rate": 5.394233904648376e-06, "loss": 0.2603, "step": 965 }, { "epoch": 3.9148936170212765, "grad_norm": 0.29449781617834325, "learning_rate": 5.355518704628997e-06, "loss": 0.2908, "step": 966 }, { "epoch": 3.9189463019250255, "grad_norm": 0.28597036074303583, "learning_rate": 5.316921449248731e-06, "loss": 0.2778, "step": 967 }, { "epoch": 3.922998986828774, "grad_norm": 0.2950318496843534, "learning_rate": 5.278442449364538e-06, "loss": 0.2609, "step": 968 }, { "epoch": 3.9270516717325226, "grad_norm": 0.2917711197709822, "learning_rate": 5.240082014881016e-06, "loss": 0.2737, "step": 969 }, { "epoch": 3.9311043566362716, "grad_norm": 0.29199580236725375, "learning_rate": 5.201840454747822e-06, "loss": 0.2592, "step": 970 }, { "epoch": 3.93515704154002, "grad_norm": 0.30946911933721954, "learning_rate": 5.163718076957223e-06, "loss": 0.2593, "step": 971 }, { "epoch": 3.939209726443769, "grad_norm": 0.3108704747518739, "learning_rate": 5.125715188541609e-06, "loss": 0.2641, "step": 972 }, { "epoch": 3.9432624113475176, "grad_norm": 0.29861649204673274, "learning_rate": 5.087832095571021e-06, "loss": 0.2624, "step": 973 }, { "epoch": 3.947315096251266, "grad_norm": 0.30024732419343236, "learning_rate": 5.0500691031506766e-06, "loss": 0.2638, "step": 974 }, { "epoch": 3.951367781155015, "grad_norm": 0.3011498867290003, "learning_rate": 5.01242651541854e-06, "loss": 0.2364, "step": 975 }, { "epoch": 3.955420466058764, "grad_norm": 0.3013776701541714, "learning_rate": 4.974904635542815e-06, "loss": 0.2454, "step": 976 }, { "epoch": 3.9594731509625127, "grad_norm": 0.2953405798688752, "learning_rate": 4.937503765719582e-06, "loss": 0.2598, "step": 977 }, { "epoch": 3.9635258358662613, "grad_norm": 0.29009471131732406, "learning_rate": 4.900224207170299e-06, "loss": 0.2526, "step": 978 }, { "epoch": 3.9675785207700103, "grad_norm": 0.28905551812716823, "learning_rate": 4.8630662601394065e-06, "loss": 0.2672, "step": 979 }, { "epoch": 3.971631205673759, "grad_norm": 0.31002558655131884, "learning_rate": 4.8260302238918995e-06, "loss": 0.2661, "step": 980 }, { "epoch": 3.975683890577508, "grad_norm": 0.2997941893957553, "learning_rate": 4.789116396710924e-06, "loss": 0.2472, "step": 981 }, { "epoch": 3.9797365754812564, "grad_norm": 0.3062649825445047, "learning_rate": 4.752325075895368e-06, "loss": 0.2444, "step": 982 }, { "epoch": 3.983789260385005, "grad_norm": 0.2969244274242138, "learning_rate": 4.715656557757473e-06, "loss": 0.256, "step": 983 }, { "epoch": 3.987841945288754, "grad_norm": 0.29835911336998316, "learning_rate": 4.679111137620442e-06, "loss": 0.2545, "step": 984 }, { "epoch": 3.9918946301925025, "grad_norm": 0.29905085994897906, "learning_rate": 4.6426891098160585e-06, "loss": 0.2523, "step": 985 }, { "epoch": 3.9959473150962515, "grad_norm": 0.29747054790618666, "learning_rate": 4.6063907676823474e-06, "loss": 0.2755, "step": 986 }, { "epoch": 4.0, "grad_norm": 0.2832719007538571, "learning_rate": 4.570216403561141e-06, "loss": 0.2674, "step": 987 }, { "epoch": 4.0040526849037485, "grad_norm": 0.49212729486349194, "learning_rate": 4.534166308795815e-06, "loss": 0.2193, "step": 988 }, { "epoch": 4.008105369807497, "grad_norm": 0.39151569717974855, "learning_rate": 4.498240773728859e-06, "loss": 0.2248, "step": 989 }, { "epoch": 4.0121580547112465, "grad_norm": 0.30516742770421834, "learning_rate": 4.462440087699609e-06, "loss": 0.1939, "step": 990 }, { "epoch": 4.016210739614995, "grad_norm": 0.31930493556115996, "learning_rate": 4.426764539041861e-06, "loss": 0.2327, "step": 991 }, { "epoch": 4.020263424518744, "grad_norm": 0.3870130938070103, "learning_rate": 4.391214415081582e-06, "loss": 0.1895, "step": 992 }, { "epoch": 4.024316109422492, "grad_norm": 0.415207616450743, "learning_rate": 4.355790002134579e-06, "loss": 0.2111, "step": 993 }, { "epoch": 4.028368794326241, "grad_norm": 0.38268577384210645, "learning_rate": 4.320491585504207e-06, "loss": 0.2107, "step": 994 }, { "epoch": 4.03242147922999, "grad_norm": 0.31157136719358164, "learning_rate": 4.2853194494790615e-06, "loss": 0.2083, "step": 995 }, { "epoch": 4.036474164133739, "grad_norm": 0.31333251481752583, "learning_rate": 4.250273877330691e-06, "loss": 0.2241, "step": 996 }, { "epoch": 4.040526849037487, "grad_norm": 0.34060503424452715, "learning_rate": 4.215355151311313e-06, "loss": 0.1918, "step": 997 }, { "epoch": 4.044579533941236, "grad_norm": 0.3268501430316943, "learning_rate": 4.180563552651542e-06, "loss": 0.1882, "step": 998 }, { "epoch": 4.048632218844984, "grad_norm": 0.3116497051026214, "learning_rate": 4.145899361558147e-06, "loss": 0.2213, "step": 999 }, { "epoch": 4.052684903748734, "grad_norm": 0.27610979982627937, "learning_rate": 4.111362857211738e-06, "loss": 0.1917, "step": 1000 }, { "epoch": 4.056737588652482, "grad_norm": 0.29400657452838874, "learning_rate": 4.076954317764592e-06, "loss": 0.2092, "step": 1001 }, { "epoch": 4.060790273556231, "grad_norm": 0.3086862509080231, "learning_rate": 4.042674020338335e-06, "loss": 0.2114, "step": 1002 }, { "epoch": 4.0648429584599794, "grad_norm": 0.3224024489703029, "learning_rate": 4.0085222410217835e-06, "loss": 0.2019, "step": 1003 }, { "epoch": 4.068895643363729, "grad_norm": 0.2705299793101589, "learning_rate": 3.974499254868674e-06, "loss": 0.1833, "step": 1004 }, { "epoch": 4.072948328267477, "grad_norm": 0.2673173816058797, "learning_rate": 3.940605335895451e-06, "loss": 0.1885, "step": 1005 }, { "epoch": 4.077001013171226, "grad_norm": 0.26974341663165635, "learning_rate": 3.90684075707908e-06, "loss": 0.1951, "step": 1006 }, { "epoch": 4.0810536980749745, "grad_norm": 0.25847740455641743, "learning_rate": 3.8732057903548505e-06, "loss": 0.207, "step": 1007 }, { "epoch": 4.085106382978723, "grad_norm": 0.28037316702706233, "learning_rate": 3.8397007066141375e-06, "loss": 0.2132, "step": 1008 }, { "epoch": 4.0891590678824725, "grad_norm": 0.2617641209902261, "learning_rate": 3.806325775702304e-06, "loss": 0.1863, "step": 1009 }, { "epoch": 4.093211752786221, "grad_norm": 0.2586032192754939, "learning_rate": 3.773081266416434e-06, "loss": 0.1968, "step": 1010 }, { "epoch": 4.09726443768997, "grad_norm": 0.253973391818422, "learning_rate": 3.739967446503245e-06, "loss": 0.2103, "step": 1011 }, { "epoch": 4.101317122593718, "grad_norm": 0.25622263586402133, "learning_rate": 3.706984582656894e-06, "loss": 0.2115, "step": 1012 }, { "epoch": 4.105369807497467, "grad_norm": 0.25934097060507016, "learning_rate": 3.6741329405168237e-06, "loss": 0.204, "step": 1013 }, { "epoch": 4.109422492401216, "grad_norm": 0.2559893678968738, "learning_rate": 3.641412784665648e-06, "loss": 0.195, "step": 1014 }, { "epoch": 4.113475177304965, "grad_norm": 0.25143638788418826, "learning_rate": 3.608824378627005e-06, "loss": 0.1981, "step": 1015 }, { "epoch": 4.117527862208713, "grad_norm": 0.2540889791223249, "learning_rate": 3.5763679848634337e-06, "loss": 0.2193, "step": 1016 }, { "epoch": 4.121580547112462, "grad_norm": 0.25212538564201203, "learning_rate": 3.544043864774269e-06, "loss": 0.2154, "step": 1017 }, { "epoch": 4.12563323201621, "grad_norm": 0.2572787015433609, "learning_rate": 3.5118522786935282e-06, "loss": 0.1858, "step": 1018 }, { "epoch": 4.12968591691996, "grad_norm": 0.2679733285844258, "learning_rate": 3.479793485887819e-06, "loss": 0.1966, "step": 1019 }, { "epoch": 4.133738601823708, "grad_norm": 0.24839021819849938, "learning_rate": 3.4478677445542653e-06, "loss": 0.2105, "step": 1020 }, { "epoch": 4.137791286727457, "grad_norm": 0.25362931971902636, "learning_rate": 3.4160753118183767e-06, "loss": 0.2125, "step": 1021 }, { "epoch": 4.141843971631205, "grad_norm": 0.24918882651482377, "learning_rate": 3.3844164437320527e-06, "loss": 0.2126, "step": 1022 }, { "epoch": 4.145896656534954, "grad_norm": 0.2399558874876352, "learning_rate": 3.3528913952714558e-06, "loss": 0.2343, "step": 1023 }, { "epoch": 4.149949341438703, "grad_norm": 0.24165090346826792, "learning_rate": 3.321500420335e-06, "loss": 0.2224, "step": 1024 }, { "epoch": 4.154002026342452, "grad_norm": 0.24893064432398765, "learning_rate": 3.290243771741275e-06, "loss": 0.2042, "step": 1025 }, { "epoch": 4.1580547112462005, "grad_norm": 0.25910848130582637, "learning_rate": 3.2591217012270325e-06, "loss": 0.1884, "step": 1026 }, { "epoch": 4.162107396149949, "grad_norm": 0.2536423379541269, "learning_rate": 3.228134459445149e-06, "loss": 0.1899, "step": 1027 }, { "epoch": 4.1661600810536985, "grad_norm": 0.2661029357187124, "learning_rate": 3.1972822959626205e-06, "loss": 0.2094, "step": 1028 }, { "epoch": 4.170212765957447, "grad_norm": 0.27076723986649215, "learning_rate": 3.166565459258513e-06, "loss": 0.1944, "step": 1029 }, { "epoch": 4.174265450861196, "grad_norm": 0.2468023705922614, "learning_rate": 3.1359841967220193e-06, "loss": 0.2221, "step": 1030 }, { "epoch": 4.178318135764944, "grad_norm": 0.26167615756092766, "learning_rate": 3.105538754650419e-06, "loss": 0.2015, "step": 1031 }, { "epoch": 4.182370820668693, "grad_norm": 0.25625855047734064, "learning_rate": 3.07522937824712e-06, "loss": 0.2086, "step": 1032 }, { "epoch": 4.186423505572442, "grad_norm": 0.2617685262388744, "learning_rate": 3.0450563116196697e-06, "loss": 0.1866, "step": 1033 }, { "epoch": 4.190476190476191, "grad_norm": 0.25373784168402314, "learning_rate": 3.0150197977778008e-06, "loss": 0.1918, "step": 1034 }, { "epoch": 4.194528875379939, "grad_norm": 0.24636857695552652, "learning_rate": 2.985120078631465e-06, "loss": 0.2092, "step": 1035 }, { "epoch": 4.198581560283688, "grad_norm": 0.2551065406718208, "learning_rate": 2.9553573949888893e-06, "loss": 0.2067, "step": 1036 }, { "epoch": 4.202634245187436, "grad_norm": 0.24854021935493217, "learning_rate": 2.9257319865546384e-06, "loss": 0.1991, "step": 1037 }, { "epoch": 4.206686930091186, "grad_norm": 0.2837436937534287, "learning_rate": 2.896244091927678e-06, "loss": 0.1982, "step": 1038 }, { "epoch": 4.210739614994934, "grad_norm": 0.23814691470808982, "learning_rate": 2.8668939485994584e-06, "loss": 0.2094, "step": 1039 }, { "epoch": 4.214792299898683, "grad_norm": 0.25539316516953253, "learning_rate": 2.837681792951994e-06, "loss": 0.1664, "step": 1040 }, { "epoch": 4.218844984802431, "grad_norm": 0.2422251662125335, "learning_rate": 2.808607860255981e-06, "loss": 0.2151, "step": 1041 }, { "epoch": 4.22289766970618, "grad_norm": 0.25345068857885406, "learning_rate": 2.7796723846688634e-06, "loss": 0.207, "step": 1042 }, { "epoch": 4.226950354609929, "grad_norm": 0.2521490357116477, "learning_rate": 2.7508755992329937e-06, "loss": 0.1845, "step": 1043 }, { "epoch": 4.231003039513678, "grad_norm": 0.23993585179346516, "learning_rate": 2.722217735873718e-06, "loss": 0.1798, "step": 1044 }, { "epoch": 4.2350557244174265, "grad_norm": 0.2508661760227835, "learning_rate": 2.6936990253975315e-06, "loss": 0.1885, "step": 1045 }, { "epoch": 4.239108409321175, "grad_norm": 0.23667653270070665, "learning_rate": 2.665319697490205e-06, "loss": 0.2049, "step": 1046 }, { "epoch": 4.243161094224924, "grad_norm": 0.23876067477757165, "learning_rate": 2.637079980714945e-06, "loss": 0.1769, "step": 1047 }, { "epoch": 4.247213779128673, "grad_norm": 0.2668315076195076, "learning_rate": 2.6089801025105453e-06, "loss": 0.182, "step": 1048 }, { "epoch": 4.251266464032422, "grad_norm": 0.2572690531504522, "learning_rate": 2.581020289189571e-06, "loss": 0.223, "step": 1049 }, { "epoch": 4.25531914893617, "grad_norm": 0.242066838041828, "learning_rate": 2.553200765936501e-06, "loss": 0.2068, "step": 1050 }, { "epoch": 4.259371833839919, "grad_norm": 0.23894822167243368, "learning_rate": 2.525521756805962e-06, "loss": 0.2155, "step": 1051 }, { "epoch": 4.263424518743667, "grad_norm": 0.24596692132728049, "learning_rate": 2.497983484720885e-06, "loss": 0.2155, "step": 1052 }, { "epoch": 4.267477203647417, "grad_norm": 0.24090147901585304, "learning_rate": 2.470586171470728e-06, "loss": 0.1905, "step": 1053 }, { "epoch": 4.271529888551165, "grad_norm": 0.24388436990543663, "learning_rate": 2.4433300377096836e-06, "loss": 0.1776, "step": 1054 }, { "epoch": 4.275582573454914, "grad_norm": 0.2423833870219351, "learning_rate": 2.4162153029549073e-06, "loss": 0.2132, "step": 1055 }, { "epoch": 4.279635258358662, "grad_norm": 0.24741593036217494, "learning_rate": 2.3892421855847458e-06, "loss": 0.1937, "step": 1056 }, { "epoch": 4.283687943262412, "grad_norm": 0.24610474684848563, "learning_rate": 2.362410902836978e-06, "loss": 0.2034, "step": 1057 }, { "epoch": 4.28774062816616, "grad_norm": 0.2594899181984098, "learning_rate": 2.3357216708070653e-06, "loss": 0.2043, "step": 1058 }, { "epoch": 4.291793313069909, "grad_norm": 0.23216297134289854, "learning_rate": 2.309174704446411e-06, "loss": 0.1868, "step": 1059 }, { "epoch": 4.295845997973657, "grad_norm": 0.23712832453290464, "learning_rate": 2.2827702175606437e-06, "loss": 0.2054, "step": 1060 }, { "epoch": 4.299898682877406, "grad_norm": 0.2507480694582349, "learning_rate": 2.256508422807855e-06, "loss": 0.2105, "step": 1061 }, { "epoch": 4.303951367781155, "grad_norm": 0.25879269677677746, "learning_rate": 2.230389531696946e-06, "loss": 0.1953, "step": 1062 }, { "epoch": 4.308004052684904, "grad_norm": 0.24680874528095242, "learning_rate": 2.204413754585857e-06, "loss": 0.196, "step": 1063 }, { "epoch": 4.3120567375886525, "grad_norm": 0.24200937644511783, "learning_rate": 2.1785813006799406e-06, "loss": 0.1873, "step": 1064 }, { "epoch": 4.316109422492401, "grad_norm": 0.2511879217821238, "learning_rate": 2.1528923780302224e-06, "loss": 0.215, "step": 1065 }, { "epoch": 4.32016210739615, "grad_norm": 0.2486178968017722, "learning_rate": 2.127347193531757e-06, "loss": 0.1986, "step": 1066 }, { "epoch": 4.324214792299899, "grad_norm": 0.24880387265465134, "learning_rate": 2.101945952921942e-06, "loss": 0.2047, "step": 1067 }, { "epoch": 4.328267477203648, "grad_norm": 0.24814884270733864, "learning_rate": 2.0766888607788906e-06, "loss": 0.1882, "step": 1068 }, { "epoch": 4.332320162107396, "grad_norm": 0.25376204863570767, "learning_rate": 2.0515761205197337e-06, "loss": 0.2145, "step": 1069 }, { "epoch": 4.336372847011145, "grad_norm": 0.2507770029501886, "learning_rate": 2.0266079343990453e-06, "loss": 0.1933, "step": 1070 }, { "epoch": 4.340425531914893, "grad_norm": 0.23553515551574122, "learning_rate": 2.0017845035071494e-06, "loss": 0.1851, "step": 1071 }, { "epoch": 4.344478216818643, "grad_norm": 0.24081197545377153, "learning_rate": 1.9771060277685537e-06, "loss": 0.2022, "step": 1072 }, { "epoch": 4.348530901722391, "grad_norm": 0.23164103310692896, "learning_rate": 1.95257270594031e-06, "loss": 0.2051, "step": 1073 }, { "epoch": 4.35258358662614, "grad_norm": 0.2507897453876342, "learning_rate": 1.9281847356104188e-06, "loss": 0.2082, "step": 1074 }, { "epoch": 4.356636271529888, "grad_norm": 0.24838376792263012, "learning_rate": 1.9039423131962365e-06, "loss": 0.1947, "step": 1075 }, { "epoch": 4.360688956433638, "grad_norm": 0.25032303766849684, "learning_rate": 1.8798456339429027e-06, "loss": 0.216, "step": 1076 }, { "epoch": 4.364741641337386, "grad_norm": 0.24665126935087092, "learning_rate": 1.8558948919217612e-06, "loss": 0.1956, "step": 1077 }, { "epoch": 4.368794326241135, "grad_norm": 0.2482312631519759, "learning_rate": 1.8320902800287954e-06, "loss": 0.1988, "step": 1078 }, { "epoch": 4.372847011144883, "grad_norm": 0.24814712740732703, "learning_rate": 1.8084319899830726e-06, "loss": 0.2081, "step": 1079 }, { "epoch": 4.376899696048632, "grad_norm": 0.24025261815548518, "learning_rate": 1.7849202123252097e-06, "loss": 0.2289, "step": 1080 }, { "epoch": 4.380952380952381, "grad_norm": 0.23612681803947239, "learning_rate": 1.7615551364158401e-06, "loss": 0.2229, "step": 1081 }, { "epoch": 4.38500506585613, "grad_norm": 0.2521152153147202, "learning_rate": 1.738336950434061e-06, "loss": 0.1934, "step": 1082 }, { "epoch": 4.3890577507598785, "grad_norm": 0.25135962207437634, "learning_rate": 1.715265841375957e-06, "loss": 0.192, "step": 1083 }, { "epoch": 4.393110435663627, "grad_norm": 0.232366600618381, "learning_rate": 1.6923419950530684e-06, "loss": 0.2174, "step": 1084 }, { "epoch": 4.397163120567376, "grad_norm": 0.2285110789006824, "learning_rate": 1.6695655960909008e-06, "loss": 0.1926, "step": 1085 }, { "epoch": 4.401215805471125, "grad_norm": 0.2567657347910915, "learning_rate": 1.646936827927441e-06, "loss": 0.2225, "step": 1086 }, { "epoch": 4.405268490374874, "grad_norm": 0.2487204408107827, "learning_rate": 1.6244558728116766e-06, "loss": 0.2065, "step": 1087 }, { "epoch": 4.409321175278622, "grad_norm": 0.24564914083082331, "learning_rate": 1.6021229118021265e-06, "loss": 0.2261, "step": 1088 }, { "epoch": 4.413373860182371, "grad_norm": 0.26121927899026226, "learning_rate": 1.5799381247653967e-06, "loss": 0.2, "step": 1089 }, { "epoch": 4.417426545086119, "grad_norm": 0.25818201502464255, "learning_rate": 1.5579016903747013e-06, "loss": 0.2062, "step": 1090 }, { "epoch": 4.421479229989869, "grad_norm": 0.2513170691588368, "learning_rate": 1.5360137861084656e-06, "loss": 0.2135, "step": 1091 }, { "epoch": 4.425531914893617, "grad_norm": 0.24214669792628418, "learning_rate": 1.5142745882488475e-06, "loss": 0.2217, "step": 1092 }, { "epoch": 4.429584599797366, "grad_norm": 0.24527753134952718, "learning_rate": 1.4926842718803691e-06, "loss": 0.1961, "step": 1093 }, { "epoch": 4.433637284701114, "grad_norm": 0.24857828641548574, "learning_rate": 1.4712430108884657e-06, "loss": 0.1946, "step": 1094 }, { "epoch": 4.437689969604863, "grad_norm": 0.2469834607983773, "learning_rate": 1.4499509779581078e-06, "loss": 0.2139, "step": 1095 }, { "epoch": 4.441742654508612, "grad_norm": 0.24956970530670186, "learning_rate": 1.4288083445723988e-06, "loss": 0.2103, "step": 1096 }, { "epoch": 4.445795339412361, "grad_norm": 0.24116317894672204, "learning_rate": 1.4078152810112045e-06, "loss": 0.1906, "step": 1097 }, { "epoch": 4.449848024316109, "grad_norm": 0.2574432423758979, "learning_rate": 1.3869719563497697e-06, "loss": 0.1688, "step": 1098 }, { "epoch": 4.453900709219858, "grad_norm": 0.2564190473657212, "learning_rate": 1.3662785384573663e-06, "loss": 0.1896, "step": 1099 }, { "epoch": 4.4579533941236065, "grad_norm": 0.24289552638331346, "learning_rate": 1.3457351939959383e-06, "loss": 0.1919, "step": 1100 }, { "epoch": 4.462006079027356, "grad_norm": 0.24724780039080202, "learning_rate": 1.3253420884187551e-06, "loss": 0.2216, "step": 1101 }, { "epoch": 4.4660587639311045, "grad_norm": 0.2407276399877983, "learning_rate": 1.3050993859690953e-06, "loss": 0.1886, "step": 1102 }, { "epoch": 4.470111448834853, "grad_norm": 0.25016173271792247, "learning_rate": 1.2850072496788869e-06, "loss": 0.1796, "step": 1103 }, { "epoch": 4.474164133738602, "grad_norm": 0.2519278638878137, "learning_rate": 1.2650658413674434e-06, "loss": 0.2143, "step": 1104 }, { "epoch": 4.47821681864235, "grad_norm": 0.2621742889948093, "learning_rate": 1.2452753216401226e-06, "loss": 0.215, "step": 1105 }, { "epoch": 4.4822695035460995, "grad_norm": 0.24452298022434485, "learning_rate": 1.2256358498870503e-06, "loss": 0.1901, "step": 1106 }, { "epoch": 4.486322188449848, "grad_norm": 0.2576015579696859, "learning_rate": 1.2061475842818337e-06, "loss": 0.2024, "step": 1107 }, { "epoch": 4.490374873353597, "grad_norm": 0.24075028414776595, "learning_rate": 1.1868106817802816e-06, "loss": 0.222, "step": 1108 }, { "epoch": 4.494427558257345, "grad_norm": 0.24831346549243255, "learning_rate": 1.1676252981191482e-06, "loss": 0.2066, "step": 1109 }, { "epoch": 4.498480243161095, "grad_norm": 0.23841893550956242, "learning_rate": 1.1485915878148823e-06, "loss": 0.184, "step": 1110 }, { "epoch": 4.502532928064843, "grad_norm": 0.25990573630755864, "learning_rate": 1.1297097041623584e-06, "loss": 0.2053, "step": 1111 }, { "epoch": 4.506585612968592, "grad_norm": 0.24923901659028547, "learning_rate": 1.1109797992336847e-06, "loss": 0.2072, "step": 1112 }, { "epoch": 4.51063829787234, "grad_norm": 0.24418909141616818, "learning_rate": 1.092402023876933e-06, "loss": 0.2055, "step": 1113 }, { "epoch": 4.514690982776089, "grad_norm": 0.24918082373793862, "learning_rate": 1.0739765277149527e-06, "loss": 0.2219, "step": 1114 }, { "epoch": 4.518743667679838, "grad_norm": 0.23760923628696845, "learning_rate": 1.0557034591441596e-06, "loss": 0.1935, "step": 1115 }, { "epoch": 4.522796352583587, "grad_norm": 0.24760590364626245, "learning_rate": 1.0375829653333324e-06, "loss": 0.1909, "step": 1116 }, { "epoch": 4.526849037487335, "grad_norm": 0.24713589140416042, "learning_rate": 1.0196151922224385e-06, "loss": 0.2113, "step": 1117 }, { "epoch": 4.530901722391084, "grad_norm": 0.26466208575599254, "learning_rate": 1.0018002845214526e-06, "loss": 0.2082, "step": 1118 }, { "epoch": 4.5349544072948325, "grad_norm": 0.25257223464006556, "learning_rate": 9.841383857091947e-07, "loss": 0.1766, "step": 1119 }, { "epoch": 4.539007092198582, "grad_norm": 0.25167998725227053, "learning_rate": 9.666296380321616e-07, "loss": 0.1998, "step": 1120 }, { "epoch": 4.54305977710233, "grad_norm": 0.2416148215010902, "learning_rate": 9.492741825034124e-07, "loss": 0.1933, "step": 1121 }, { "epoch": 4.547112462006079, "grad_norm": 0.25706651350908744, "learning_rate": 9.320721589013892e-07, "loss": 0.1978, "step": 1122 }, { "epoch": 4.5511651469098275, "grad_norm": 0.23673547041483708, "learning_rate": 9.150237057688339e-07, "loss": 0.1925, "step": 1123 }, { "epoch": 4.555217831813577, "grad_norm": 0.24777510116778528, "learning_rate": 8.981289604116328e-07, "loss": 0.1922, "step": 1124 }, { "epoch": 4.5592705167173255, "grad_norm": 0.2549886668392779, "learning_rate": 8.813880588977542e-07, "loss": 0.1737, "step": 1125 }, { "epoch": 4.563323201621074, "grad_norm": 0.24941224040718177, "learning_rate": 8.648011360561126e-07, "loss": 0.2086, "step": 1126 }, { "epoch": 4.567375886524823, "grad_norm": 0.25008647508496457, "learning_rate": 8.483683254755037e-07, "loss": 0.202, "step": 1127 }, { "epoch": 4.571428571428571, "grad_norm": 0.24304549771387748, "learning_rate": 8.320897595035227e-07, "loss": 0.2222, "step": 1128 }, { "epoch": 4.575481256332321, "grad_norm": 0.2444987304766229, "learning_rate": 8.159655692455093e-07, "loss": 0.194, "step": 1129 }, { "epoch": 4.579533941236069, "grad_norm": 0.2604206956706893, "learning_rate": 7.999958845634648e-07, "loss": 0.2142, "step": 1130 }, { "epoch": 4.583586626139818, "grad_norm": 0.25309715388414655, "learning_rate": 7.841808340750478e-07, "loss": 0.2119, "step": 1131 }, { "epoch": 4.587639311043566, "grad_norm": 0.24790481602710543, "learning_rate": 7.685205451524869e-07, "loss": 0.2086, "step": 1132 }, { "epoch": 4.591691995947315, "grad_norm": 0.24983535654820474, "learning_rate": 7.530151439216027e-07, "loss": 0.1787, "step": 1133 }, { "epoch": 4.595744680851064, "grad_norm": 0.2486891997934812, "learning_rate": 7.376647552607675e-07, "loss": 0.1987, "step": 1134 }, { "epoch": 4.599797365754813, "grad_norm": 0.2326434459898208, "learning_rate": 7.224695027998963e-07, "loss": 0.181, "step": 1135 }, { "epoch": 4.603850050658561, "grad_norm": 0.24054877749576015, "learning_rate": 7.07429508919466e-07, "loss": 0.2013, "step": 1136 }, { "epoch": 4.60790273556231, "grad_norm": 0.24846389224889026, "learning_rate": 6.925448947495206e-07, "loss": 0.1944, "step": 1137 }, { "epoch": 4.611955420466058, "grad_norm": 0.24660112392711814, "learning_rate": 6.778157801686936e-07, "loss": 0.1982, "step": 1138 }, { "epoch": 4.616008105369808, "grad_norm": 0.2596039992836043, "learning_rate": 6.632422838032515e-07, "loss": 0.2163, "step": 1139 }, { "epoch": 4.620060790273556, "grad_norm": 0.24965207189531147, "learning_rate": 6.488245230261281e-07, "loss": 0.1899, "step": 1140 }, { "epoch": 4.624113475177305, "grad_norm": 0.22996459963899185, "learning_rate": 6.345626139559868e-07, "loss": 0.1842, "step": 1141 }, { "epoch": 4.6281661600810535, "grad_norm": 0.24344591612958302, "learning_rate": 6.204566714562866e-07, "loss": 0.2231, "step": 1142 }, { "epoch": 4.632218844984802, "grad_norm": 0.2501881839782138, "learning_rate": 6.06506809134344e-07, "loss": 0.1898, "step": 1143 }, { "epoch": 4.6362715298885515, "grad_norm": 0.2390439307860063, "learning_rate": 5.927131393404373e-07, "loss": 0.1942, "step": 1144 }, { "epoch": 4.6403242147923, "grad_norm": 0.23859296216820156, "learning_rate": 5.790757731668817e-07, "loss": 0.2083, "step": 1145 }, { "epoch": 4.644376899696049, "grad_norm": 0.25156654012233953, "learning_rate": 5.655948204471507e-07, "loss": 0.19, "step": 1146 }, { "epoch": 4.648429584599797, "grad_norm": 0.24935521485438975, "learning_rate": 5.522703897549875e-07, "loss": 0.1851, "step": 1147 }, { "epoch": 4.652482269503546, "grad_norm": 0.24987385132029152, "learning_rate": 5.391025884035239e-07, "loss": 0.2114, "step": 1148 }, { "epoch": 4.656534954407295, "grad_norm": 0.23979057308566046, "learning_rate": 5.260915224444207e-07, "loss": 0.2016, "step": 1149 }, { "epoch": 4.660587639311044, "grad_norm": 0.24037457816555458, "learning_rate": 5.132372966670129e-07, "loss": 0.198, "step": 1150 }, { "epoch": 4.664640324214792, "grad_norm": 0.24662597536979464, "learning_rate": 5.005400145974704e-07, "loss": 0.1991, "step": 1151 }, { "epoch": 4.668693009118541, "grad_norm": 0.2456610686526762, "learning_rate": 4.879997784979562e-07, "loss": 0.1987, "step": 1152 }, { "epoch": 4.672745694022289, "grad_norm": 0.23818091118705748, "learning_rate": 4.7561668936580984e-07, "loss": 0.1857, "step": 1153 }, { "epoch": 4.676798378926039, "grad_norm": 0.23870037125444504, "learning_rate": 4.6339084693272306e-07, "loss": 0.2015, "step": 1154 }, { "epoch": 4.680851063829787, "grad_norm": 0.2426180811096015, "learning_rate": 4.5132234966395847e-07, "loss": 0.2294, "step": 1155 }, { "epoch": 4.684903748733536, "grad_norm": 0.2444717883510916, "learning_rate": 4.3941129475752795e-07, "loss": 0.1949, "step": 1156 }, { "epoch": 4.688956433637284, "grad_norm": 0.23867256875477824, "learning_rate": 4.27657778143431e-07, "loss": 0.1925, "step": 1157 }, { "epoch": 4.693009118541033, "grad_norm": 0.24415027130155562, "learning_rate": 4.1606189448287757e-07, "loss": 0.1972, "step": 1158 }, { "epoch": 4.697061803444782, "grad_norm": 0.24512888367198166, "learning_rate": 4.046237371675177e-07, "loss": 0.1974, "step": 1159 }, { "epoch": 4.701114488348531, "grad_norm": 0.2481879364227404, "learning_rate": 3.9334339831869963e-07, "loss": 0.2024, "step": 1160 }, { "epoch": 4.7051671732522795, "grad_norm": 0.2407595092163603, "learning_rate": 3.8222096878671955e-07, "loss": 0.1736, "step": 1161 }, { "epoch": 4.709219858156028, "grad_norm": 0.23931711755408194, "learning_rate": 3.7125653815009545e-07, "loss": 0.191, "step": 1162 }, { "epoch": 4.713272543059777, "grad_norm": 0.24888033224975037, "learning_rate": 3.6045019471484974e-07, "loss": 0.207, "step": 1163 }, { "epoch": 4.717325227963526, "grad_norm": 0.25125223432810573, "learning_rate": 3.498020255137813e-07, "loss": 0.1998, "step": 1164 }, { "epoch": 4.721377912867275, "grad_norm": 0.2565517772478762, "learning_rate": 3.393121163057811e-07, "loss": 0.1988, "step": 1165 }, { "epoch": 4.725430597771023, "grad_norm": 0.2527112386006553, "learning_rate": 3.289805515751399e-07, "loss": 0.1969, "step": 1166 }, { "epoch": 4.729483282674772, "grad_norm": 0.2447049153289079, "learning_rate": 3.188074145308573e-07, "loss": 0.2001, "step": 1167 }, { "epoch": 4.733535967578521, "grad_norm": 0.2515366216607944, "learning_rate": 3.087927871059804e-07, "loss": 0.2106, "step": 1168 }, { "epoch": 4.73758865248227, "grad_norm": 0.25284169932128453, "learning_rate": 2.989367499569418e-07, "loss": 0.1921, "step": 1169 }, { "epoch": 4.741641337386018, "grad_norm": 2.1158282294024806, "learning_rate": 2.8923938246290917e-07, "loss": 0.231, "step": 1170 }, { "epoch": 4.745694022289767, "grad_norm": 0.25472104100072057, "learning_rate": 2.7970076272514804e-07, "loss": 0.1957, "step": 1171 }, { "epoch": 4.749746707193515, "grad_norm": 0.2427726194796699, "learning_rate": 2.703209675663887e-07, "loss": 0.1866, "step": 1172 }, { "epoch": 4.753799392097265, "grad_norm": 0.25159398007209016, "learning_rate": 2.6110007253021374e-07, "loss": 0.1964, "step": 1173 }, { "epoch": 4.757852077001013, "grad_norm": 0.24834947573666064, "learning_rate": 2.520381518804471e-07, "loss": 0.2278, "step": 1174 }, { "epoch": 4.761904761904762, "grad_norm": 0.24389835262032514, "learning_rate": 2.4313527860054585e-07, "loss": 0.1955, "step": 1175 }, { "epoch": 4.76595744680851, "grad_norm": 0.24040244441202888, "learning_rate": 2.343915243930317e-07, "loss": 0.1956, "step": 1176 }, { "epoch": 4.77001013171226, "grad_norm": 0.2445642021300155, "learning_rate": 2.2580695967889367e-07, "loss": 0.1989, "step": 1177 }, { "epoch": 4.774062816616008, "grad_norm": 0.23649243767505182, "learning_rate": 2.1738165359704189e-07, "loss": 0.1781, "step": 1178 }, { "epoch": 4.778115501519757, "grad_norm": 0.24444891340051922, "learning_rate": 2.0911567400373257e-07, "loss": 0.1858, "step": 1179 }, { "epoch": 4.7821681864235055, "grad_norm": 0.24272706127774726, "learning_rate": 2.0100908747202607e-07, "loss": 0.1956, "step": 1180 }, { "epoch": 4.786220871327254, "grad_norm": 0.23992042016885853, "learning_rate": 1.9306195929125638e-07, "loss": 0.2221, "step": 1181 }, { "epoch": 4.7902735562310035, "grad_norm": 0.24110345991491774, "learning_rate": 1.8527435346650247e-07, "loss": 0.185, "step": 1182 }, { "epoch": 4.794326241134752, "grad_norm": 0.2549465246377265, "learning_rate": 1.7764633271807108e-07, "loss": 0.229, "step": 1183 }, { "epoch": 4.798378926038501, "grad_norm": 0.23452676157526703, "learning_rate": 1.7017795848099262e-07, "loss": 0.2014, "step": 1184 }, { "epoch": 4.802431610942249, "grad_norm": 0.24613568698781021, "learning_rate": 1.6286929090452596e-07, "loss": 0.2178, "step": 1185 }, { "epoch": 4.806484295845998, "grad_norm": 0.24642812766695082, "learning_rate": 1.557203888516745e-07, "loss": 0.206, "step": 1186 }, { "epoch": 4.810536980749747, "grad_norm": 0.24480746434735134, "learning_rate": 1.487313098987131e-07, "loss": 0.1674, "step": 1187 }, { "epoch": 4.814589665653496, "grad_norm": 0.2486845959874826, "learning_rate": 1.4190211033472402e-07, "loss": 0.1902, "step": 1188 }, { "epoch": 4.818642350557244, "grad_norm": 0.24701531634013274, "learning_rate": 1.3523284516113955e-07, "loss": 0.1965, "step": 1189 }, { "epoch": 4.822695035460993, "grad_norm": 0.2424354515002044, "learning_rate": 1.2872356809130682e-07, "loss": 0.1938, "step": 1190 }, { "epoch": 4.826747720364741, "grad_norm": 0.24401263259008535, "learning_rate": 1.2237433155004807e-07, "loss": 0.1921, "step": 1191 }, { "epoch": 4.830800405268491, "grad_norm": 0.24629042509856183, "learning_rate": 1.1618518667323886e-07, "loss": 0.1929, "step": 1192 }, { "epoch": 4.834853090172239, "grad_norm": 0.24527351576465922, "learning_rate": 1.1015618330740385e-07, "loss": 0.2104, "step": 1193 }, { "epoch": 4.838905775075988, "grad_norm": 0.24993420923356927, "learning_rate": 1.042873700093061e-07, "loss": 0.1914, "step": 1194 }, { "epoch": 4.842958459979736, "grad_norm": 0.24024907494801329, "learning_rate": 9.857879404556291e-08, "loss": 0.2269, "step": 1195 }, { "epoch": 4.847011144883485, "grad_norm": 0.25262749541050683, "learning_rate": 9.303050139225722e-08, "loss": 0.1923, "step": 1196 }, { "epoch": 4.851063829787234, "grad_norm": 0.2502138454239054, "learning_rate": 8.76425367345779e-08, "loss": 0.1937, "step": 1197 }, { "epoch": 4.855116514690983, "grad_norm": 0.2441087087629779, "learning_rate": 8.241494346644897e-08, "loss": 0.2177, "step": 1198 }, { "epoch": 4.8591691995947315, "grad_norm": 0.2470489245010094, "learning_rate": 7.734776369019204e-08, "loss": 0.2337, "step": 1199 }, { "epoch": 4.86322188449848, "grad_norm": 0.24277599122670662, "learning_rate": 7.244103821617332e-08, "loss": 0.1925, "step": 1200 }, { "epoch": 4.867274569402229, "grad_norm": 0.2452426942002828, "learning_rate": 6.769480656248606e-08, "loss": 0.2032, "step": 1201 }, { "epoch": 4.871327254305978, "grad_norm": 0.2431359346503819, "learning_rate": 6.310910695462635e-08, "loss": 0.2136, "step": 1202 }, { "epoch": 4.875379939209727, "grad_norm": 0.23683916021804133, "learning_rate": 5.8683976325191185e-08, "loss": 0.1942, "step": 1203 }, { "epoch": 4.879432624113475, "grad_norm": 0.2350404087337152, "learning_rate": 5.4419450313571984e-08, "loss": 0.2163, "step": 1204 }, { "epoch": 4.883485309017224, "grad_norm": 0.23309890859786067, "learning_rate": 5.031556326567488e-08, "loss": 0.1901, "step": 1205 }, { "epoch": 4.887537993920972, "grad_norm": 0.25201277765073227, "learning_rate": 4.637234823364312e-08, "loss": 0.2129, "step": 1206 }, { "epoch": 4.891590678824722, "grad_norm": 0.2486182262508644, "learning_rate": 4.258983697558838e-08, "loss": 0.1876, "step": 1207 }, { "epoch": 4.89564336372847, "grad_norm": 0.24556936656999018, "learning_rate": 3.896805995533548e-08, "loss": 0.1834, "step": 1208 }, { "epoch": 4.899696048632219, "grad_norm": 0.24004525286969983, "learning_rate": 3.550704634218028e-08, "loss": 0.1911, "step": 1209 }, { "epoch": 4.903748733535967, "grad_norm": 0.24133164614908817, "learning_rate": 3.2206824010647676e-08, "loss": 0.1755, "step": 1210 }, { "epoch": 4.907801418439716, "grad_norm": 0.25036437458547406, "learning_rate": 2.9067419540278476e-08, "loss": 0.196, "step": 1211 }, { "epoch": 4.911854103343465, "grad_norm": 0.22127798453587197, "learning_rate": 2.6088858215400638e-08, "loss": 0.2032, "step": 1212 }, { "epoch": 4.915906788247214, "grad_norm": 0.24441260961978103, "learning_rate": 2.3271164024940564e-08, "loss": 0.2098, "step": 1213 }, { "epoch": 4.919959473150962, "grad_norm": 0.25003024386568296, "learning_rate": 2.061435966221881e-08, "loss": 0.1948, "step": 1214 }, { "epoch": 4.924012158054711, "grad_norm": 0.24705718545387664, "learning_rate": 1.811846652477245e-08, "loss": 0.195, "step": 1215 }, { "epoch": 4.92806484295846, "grad_norm": 0.24203127006993658, "learning_rate": 1.5783504714184106e-08, "loss": 0.185, "step": 1216 }, { "epoch": 4.932117527862209, "grad_norm": 0.23786465472707058, "learning_rate": 1.360949303591097e-08, "loss": 0.2079, "step": 1217 }, { "epoch": 4.9361702127659575, "grad_norm": 0.24715321065178558, "learning_rate": 1.1596448999144916e-08, "loss": 0.2115, "step": 1218 }, { "epoch": 4.940222897669706, "grad_norm": 0.2327120001547924, "learning_rate": 9.744388816668172e-09, "loss": 0.209, "step": 1219 }, { "epoch": 4.944275582573455, "grad_norm": 0.24613180956749753, "learning_rate": 8.05332740472009e-09, "loss": 0.195, "step": 1220 }, { "epoch": 4.948328267477204, "grad_norm": 0.23745813993145284, "learning_rate": 6.523278382872811e-09, "loss": 0.1935, "step": 1221 }, { "epoch": 4.9523809523809526, "grad_norm": 0.2538165192899779, "learning_rate": 5.15425407393133e-09, "loss": 0.1985, "step": 1222 }, { "epoch": 4.956433637284701, "grad_norm": 0.25351330451303256, "learning_rate": 3.94626550383137e-09, "loss": 0.2075, "step": 1223 }, { "epoch": 4.96048632218845, "grad_norm": 0.232080317939174, "learning_rate": 2.899322401546112e-09, "loss": 0.204, "step": 1224 }, { "epoch": 4.964539007092198, "grad_norm": 0.24489195445340936, "learning_rate": 2.013433199010706e-09, "loss": 0.228, "step": 1225 }, { "epoch": 4.968591691995948, "grad_norm": 0.24726830604237326, "learning_rate": 1.2886050310556563e-09, "loss": 0.1984, "step": 1226 }, { "epoch": 4.972644376899696, "grad_norm": 0.2637378330237958, "learning_rate": 7.248437353468695e-10, "loss": 0.2205, "step": 1227 }, { "epoch": 4.976697061803445, "grad_norm": 0.23905412846927215, "learning_rate": 3.221538523412449e-10, "loss": 0.2175, "step": 1228 }, { "epoch": 4.980749746707193, "grad_norm": 0.23591072567055912, "learning_rate": 8.053862524670663e-11, "loss": 0.1928, "step": 1229 }, { "epoch": 4.984802431610943, "grad_norm": 0.24535295960413284, "learning_rate": 0.0, "loss": 0.1872, "step": 1230 }, { "epoch": 4.984802431610943, "step": 1230, "total_flos": 2.5001335726405714e+18, "train_loss": 0.4134981281389066, "train_runtime": 24880.2523, "train_samples_per_second": 6.345, "train_steps_per_second": 0.049 } ], "logging_steps": 1, "max_steps": 1230, "num_input_tokens_seen": 0, "num_train_epochs": 5, "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": 2.5001335726405714e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }