{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 200, "global_step": 668, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0029940119760479044, "grad_norm": 3.659729551431091, "learning_rate": 9.999944704978835e-06, "loss": 0.2271, "step": 1 }, { "epoch": 0.005988023952095809, "grad_norm": 2.9390745439158525, "learning_rate": 9.999778821138357e-06, "loss": 0.1712, "step": 2 }, { "epoch": 0.008982035928143712, "grad_norm": 3.1888534837983706, "learning_rate": 9.999502352147583e-06, "loss": 0.218, "step": 3 }, { "epoch": 0.011976047904191617, "grad_norm": 3.063975979406656, "learning_rate": 9.999115304121459e-06, "loss": 0.1713, "step": 4 }, { "epoch": 0.014970059880239521, "grad_norm": 3.230299116383101, "learning_rate": 9.998617685620715e-06, "loss": 0.1675, "step": 5 }, { "epoch": 0.017964071856287425, "grad_norm": 3.1010709459555934, "learning_rate": 9.998009507651683e-06, "loss": 0.1595, "step": 6 }, { "epoch": 0.020958083832335328, "grad_norm": 3.3485814838746015, "learning_rate": 9.997290783666048e-06, "loss": 0.1775, "step": 7 }, { "epoch": 0.023952095808383235, "grad_norm": 3.093673935459984, "learning_rate": 9.996461529560553e-06, "loss": 0.1651, "step": 8 }, { "epoch": 0.02694610778443114, "grad_norm": 3.232838744381857, "learning_rate": 9.995521763676645e-06, "loss": 0.1961, "step": 9 }, { "epoch": 0.029940119760479042, "grad_norm": 3.637671964911181, "learning_rate": 9.994471506800078e-06, "loss": 0.1705, "step": 10 }, { "epoch": 0.03293413173652695, "grad_norm": 2.948870505940658, "learning_rate": 9.993310782160439e-06, "loss": 0.1838, "step": 11 }, { "epoch": 0.03592814371257485, "grad_norm": 3.1768290478208074, "learning_rate": 9.992039615430648e-06, "loss": 0.1625, "step": 12 }, { "epoch": 0.038922155688622756, "grad_norm": 2.9480453789224104, "learning_rate": 9.99065803472638e-06, "loss": 0.1895, "step": 13 }, { "epoch": 0.041916167664670656, "grad_norm": 3.2714817847768787, "learning_rate": 9.989166070605447e-06, "loss": 0.1884, "step": 14 }, { "epoch": 0.04491017964071856, "grad_norm": 3.124678649197469, "learning_rate": 9.98756375606713e-06, "loss": 0.1612, "step": 15 }, { "epoch": 0.04790419161676647, "grad_norm": 3.082387404660864, "learning_rate": 9.985851126551428e-06, "loss": 0.1843, "step": 16 }, { "epoch": 0.05089820359281437, "grad_norm": 2.4744843791169067, "learning_rate": 9.9840282199383e-06, "loss": 0.1401, "step": 17 }, { "epoch": 0.05389221556886228, "grad_norm": 3.0846262963772233, "learning_rate": 9.982095076546806e-06, "loss": 0.2015, "step": 18 }, { "epoch": 0.05688622754491018, "grad_norm": 3.601073265043088, "learning_rate": 9.980051739134235e-06, "loss": 0.2017, "step": 19 }, { "epoch": 0.059880239520958084, "grad_norm": 2.892042736941296, "learning_rate": 9.977898252895133e-06, "loss": 0.1886, "step": 20 }, { "epoch": 0.06287425149700598, "grad_norm": 2.894732287460309, "learning_rate": 9.975634665460333e-06, "loss": 0.1935, "step": 21 }, { "epoch": 0.0658682634730539, "grad_norm": 3.1539134789680654, "learning_rate": 9.973261026895878e-06, "loss": 0.2057, "step": 22 }, { "epoch": 0.0688622754491018, "grad_norm": 2.7343901870027048, "learning_rate": 9.970777389701927e-06, "loss": 0.1927, "step": 23 }, { "epoch": 0.0718562874251497, "grad_norm": 2.5554328799399046, "learning_rate": 9.968183808811586e-06, "loss": 0.1544, "step": 24 }, { "epoch": 0.0748502994011976, "grad_norm": 2.981304193526295, "learning_rate": 9.965480341589702e-06, "loss": 0.1748, "step": 25 }, { "epoch": 0.07784431137724551, "grad_norm": 3.1674761155014655, "learning_rate": 9.962667047831585e-06, "loss": 0.1893, "step": 26 }, { "epoch": 0.08083832335329341, "grad_norm": 2.9602331006849, "learning_rate": 9.95974398976169e-06, "loss": 0.2029, "step": 27 }, { "epoch": 0.08383233532934131, "grad_norm": 2.808129484842409, "learning_rate": 9.95671123203224e-06, "loss": 0.1884, "step": 28 }, { "epoch": 0.08682634730538923, "grad_norm": 2.913173177734654, "learning_rate": 9.953568841721796e-06, "loss": 0.1846, "step": 29 }, { "epoch": 0.08982035928143713, "grad_norm": 2.680883034025124, "learning_rate": 9.950316888333775e-06, "loss": 0.1848, "step": 30 }, { "epoch": 0.09281437125748503, "grad_norm": 2.241359131108658, "learning_rate": 9.946955443794908e-06, "loss": 0.174, "step": 31 }, { "epoch": 0.09580838323353294, "grad_norm": 3.33117902481845, "learning_rate": 9.943484582453653e-06, "loss": 0.1804, "step": 32 }, { "epoch": 0.09880239520958084, "grad_norm": 3.0410646363730636, "learning_rate": 9.939904381078553e-06, "loss": 0.1612, "step": 33 }, { "epoch": 0.10179640718562874, "grad_norm": 3.1142432178428603, "learning_rate": 9.93621491885653e-06, "loss": 0.204, "step": 34 }, { "epoch": 0.10479041916167664, "grad_norm": 2.9317534184302296, "learning_rate": 9.932416277391144e-06, "loss": 0.168, "step": 35 }, { "epoch": 0.10778443113772455, "grad_norm": 3.027999878799591, "learning_rate": 9.928508540700775e-06, "loss": 0.1902, "step": 36 }, { "epoch": 0.11077844311377245, "grad_norm": 3.603601529584119, "learning_rate": 9.924491795216777e-06, "loss": 0.2184, "step": 37 }, { "epoch": 0.11377245508982035, "grad_norm": 2.9507020367147523, "learning_rate": 9.920366129781564e-06, "loss": 0.1802, "step": 38 }, { "epoch": 0.11676646706586827, "grad_norm": 2.269330766787671, "learning_rate": 9.916131635646635e-06, "loss": 0.1523, "step": 39 }, { "epoch": 0.11976047904191617, "grad_norm": 2.8807661036995618, "learning_rate": 9.91178840647057e-06, "loss": 0.181, "step": 40 }, { "epoch": 0.12275449101796407, "grad_norm": 2.5509379479540275, "learning_rate": 9.907336538316946e-06, "loss": 0.1966, "step": 41 }, { "epoch": 0.12574850299401197, "grad_norm": 2.4318851363055196, "learning_rate": 9.902776129652223e-06, "loss": 0.1376, "step": 42 }, { "epoch": 0.12874251497005987, "grad_norm": 2.711956693936677, "learning_rate": 9.898107281343557e-06, "loss": 0.1628, "step": 43 }, { "epoch": 0.1317365269461078, "grad_norm": 2.5207518221608645, "learning_rate": 9.893330096656576e-06, "loss": 0.1463, "step": 44 }, { "epoch": 0.1347305389221557, "grad_norm": 3.238109773584591, "learning_rate": 9.888444681253087e-06, "loss": 0.177, "step": 45 }, { "epoch": 0.1377245508982036, "grad_norm": 3.138436536444299, "learning_rate": 9.883451143188753e-06, "loss": 0.1847, "step": 46 }, { "epoch": 0.1407185628742515, "grad_norm": 2.892561291546367, "learning_rate": 9.878349592910694e-06, "loss": 0.1718, "step": 47 }, { "epoch": 0.1437125748502994, "grad_norm": 3.5379179798790354, "learning_rate": 9.873140143255035e-06, "loss": 0.2071, "step": 48 }, { "epoch": 0.1467065868263473, "grad_norm": 2.940774093942888, "learning_rate": 9.867822909444435e-06, "loss": 0.2067, "step": 49 }, { "epoch": 0.1497005988023952, "grad_norm": 2.804341866261009, "learning_rate": 9.862398009085511e-06, "loss": 0.166, "step": 50 }, { "epoch": 0.15269461077844312, "grad_norm": 2.6578245501607483, "learning_rate": 9.856865562166256e-06, "loss": 0.1773, "step": 51 }, { "epoch": 0.15568862275449102, "grad_norm": 2.4976586990745853, "learning_rate": 9.851225691053382e-06, "loss": 0.1595, "step": 52 }, { "epoch": 0.15868263473053892, "grad_norm": 2.895296930977589, "learning_rate": 9.8454785204896e-06, "loss": 0.215, "step": 53 }, { "epoch": 0.16167664670658682, "grad_norm": 2.587123841400067, "learning_rate": 9.83962417759088e-06, "loss": 0.1621, "step": 54 }, { "epoch": 0.16467065868263472, "grad_norm": 3.014031207264, "learning_rate": 9.833662791843628e-06, "loss": 0.1671, "step": 55 }, { "epoch": 0.16766467065868262, "grad_norm": 2.7527623724195958, "learning_rate": 9.827594495101824e-06, "loss": 0.1863, "step": 56 }, { "epoch": 0.17065868263473055, "grad_norm": 3.007624378123238, "learning_rate": 9.821419421584108e-06, "loss": 0.1981, "step": 57 }, { "epoch": 0.17365269461077845, "grad_norm": 3.1636795485487776, "learning_rate": 9.815137707870806e-06, "loss": 0.2747, "step": 58 }, { "epoch": 0.17664670658682635, "grad_norm": 2.978323631591701, "learning_rate": 9.808749492900917e-06, "loss": 0.1944, "step": 59 }, { "epoch": 0.17964071856287425, "grad_norm": 2.7963703118232925, "learning_rate": 9.802254917969033e-06, "loss": 0.1902, "step": 60 }, { "epoch": 0.18263473053892215, "grad_norm": 3.152972474091335, "learning_rate": 9.795654126722218e-06, "loss": 0.2102, "step": 61 }, { "epoch": 0.18562874251497005, "grad_norm": 2.8249792544576784, "learning_rate": 9.788947265156828e-06, "loss": 0.1728, "step": 62 }, { "epoch": 0.18862275449101795, "grad_norm": 2.643898174692706, "learning_rate": 9.782134481615282e-06, "loss": 0.1431, "step": 63 }, { "epoch": 0.19161676646706588, "grad_norm": 2.549213228332548, "learning_rate": 9.775215926782788e-06, "loss": 0.1958, "step": 64 }, { "epoch": 0.19461077844311378, "grad_norm": 2.813394155651819, "learning_rate": 9.768191753683997e-06, "loss": 0.1826, "step": 65 }, { "epoch": 0.19760479041916168, "grad_norm": 2.48437350768464, "learning_rate": 9.761062117679632e-06, "loss": 0.1807, "step": 66 }, { "epoch": 0.20059880239520958, "grad_norm": 2.7572077191834117, "learning_rate": 9.75382717646304e-06, "loss": 0.1854, "step": 67 }, { "epoch": 0.20359281437125748, "grad_norm": 2.520586312711251, "learning_rate": 9.746487090056712e-06, "loss": 0.1669, "step": 68 }, { "epoch": 0.20658682634730538, "grad_norm": 2.5166910942052, "learning_rate": 9.739042020808746e-06, "loss": 0.1707, "step": 69 }, { "epoch": 0.20958083832335328, "grad_norm": 2.787685370378393, "learning_rate": 9.73149213338924e-06, "loss": 0.1947, "step": 70 }, { "epoch": 0.2125748502994012, "grad_norm": 3.116243889129261, "learning_rate": 9.72383759478667e-06, "loss": 0.2113, "step": 71 }, { "epoch": 0.2155688622754491, "grad_norm": 2.7383217193289955, "learning_rate": 9.71607857430419e-06, "loss": 0.1268, "step": 72 }, { "epoch": 0.218562874251497, "grad_norm": 3.0597366161067114, "learning_rate": 9.708215243555875e-06, "loss": 0.2098, "step": 73 }, { "epoch": 0.2215568862275449, "grad_norm": 3.02338339319515, "learning_rate": 9.700247776462944e-06, "loss": 0.1661, "step": 74 }, { "epoch": 0.2245508982035928, "grad_norm": 2.859853363963014, "learning_rate": 9.6921763492499e-06, "loss": 0.1742, "step": 75 }, { "epoch": 0.2275449101796407, "grad_norm": 2.5511374557220945, "learning_rate": 9.68400114044064e-06, "loss": 0.1275, "step": 76 }, { "epoch": 0.23053892215568864, "grad_norm": 2.881086712178579, "learning_rate": 9.6757223308545e-06, "loss": 0.1523, "step": 77 }, { "epoch": 0.23353293413173654, "grad_norm": 2.7495759847540695, "learning_rate": 9.667340103602263e-06, "loss": 0.1965, "step": 78 }, { "epoch": 0.23652694610778444, "grad_norm": 2.885254869004917, "learning_rate": 9.658854644082099e-06, "loss": 0.178, "step": 79 }, { "epoch": 0.23952095808383234, "grad_norm": 3.446926261602067, "learning_rate": 9.650266139975474e-06, "loss": 0.2243, "step": 80 }, { "epoch": 0.24251497005988024, "grad_norm": 2.672359051431842, "learning_rate": 9.641574781242999e-06, "loss": 0.1719, "step": 81 }, { "epoch": 0.24550898203592814, "grad_norm": 2.4682177721398664, "learning_rate": 9.632780760120217e-06, "loss": 0.1507, "step": 82 }, { "epoch": 0.24850299401197604, "grad_norm": 2.628264330953761, "learning_rate": 9.62388427111336e-06, "loss": 0.1677, "step": 83 }, { "epoch": 0.25149700598802394, "grad_norm": 2.3885030250193684, "learning_rate": 9.614885510995047e-06, "loss": 0.1418, "step": 84 }, { "epoch": 0.25449101796407186, "grad_norm": 2.5175326584383795, "learning_rate": 9.605784678799934e-06, "loss": 0.1534, "step": 85 }, { "epoch": 0.25748502994011974, "grad_norm": 3.1389738453005696, "learning_rate": 9.596581975820304e-06, "loss": 0.1669, "step": 86 }, { "epoch": 0.26047904191616766, "grad_norm": 2.5959270432114665, "learning_rate": 9.587277605601617e-06, "loss": 0.1691, "step": 87 }, { "epoch": 0.2634730538922156, "grad_norm": 3.2278752436233074, "learning_rate": 9.577871773938013e-06, "loss": 0.1895, "step": 88 }, { "epoch": 0.26646706586826346, "grad_norm": 2.864147741203854, "learning_rate": 9.568364688867757e-06, "loss": 0.2267, "step": 89 }, { "epoch": 0.2694610778443114, "grad_norm": 2.4536338997481595, "learning_rate": 9.558756560668637e-06, "loss": 0.1607, "step": 90 }, { "epoch": 0.27245508982035926, "grad_norm": 2.9730744063772927, "learning_rate": 9.549047601853313e-06, "loss": 0.1875, "step": 91 }, { "epoch": 0.2754491017964072, "grad_norm": 2.792412333768772, "learning_rate": 9.539238027164618e-06, "loss": 0.183, "step": 92 }, { "epoch": 0.27844311377245506, "grad_norm": 2.545839392688853, "learning_rate": 9.52932805357081e-06, "loss": 0.1597, "step": 93 }, { "epoch": 0.281437125748503, "grad_norm": 2.5394073244820645, "learning_rate": 9.519317900260769e-06, "loss": 0.1719, "step": 94 }, { "epoch": 0.2844311377245509, "grad_norm": 2.4354087273786824, "learning_rate": 9.509207788639148e-06, "loss": 0.1674, "step": 95 }, { "epoch": 0.2874251497005988, "grad_norm": 2.3814472796469466, "learning_rate": 9.498997942321484e-06, "loss": 0.1891, "step": 96 }, { "epoch": 0.2904191616766467, "grad_norm": 2.4314076281356747, "learning_rate": 9.488688587129243e-06, "loss": 0.1669, "step": 97 }, { "epoch": 0.2934131736526946, "grad_norm": 2.490413429200047, "learning_rate": 9.47827995108483e-06, "loss": 0.1424, "step": 98 }, { "epoch": 0.2964071856287425, "grad_norm": 2.934010579126374, "learning_rate": 9.467772264406545e-06, "loss": 0.197, "step": 99 }, { "epoch": 0.2994011976047904, "grad_norm": 2.5539143602532204, "learning_rate": 9.457165759503492e-06, "loss": 0.152, "step": 100 }, { "epoch": 0.3023952095808383, "grad_norm": 2.750248302538589, "learning_rate": 9.446460670970436e-06, "loss": 0.1465, "step": 101 }, { "epoch": 0.30538922155688625, "grad_norm": 2.614579048432019, "learning_rate": 9.435657235582616e-06, "loss": 0.1385, "step": 102 }, { "epoch": 0.3083832335329341, "grad_norm": 2.962247506504664, "learning_rate": 9.424755692290507e-06, "loss": 0.1779, "step": 103 }, { "epoch": 0.31137724550898205, "grad_norm": 2.7813903320317444, "learning_rate": 9.413756282214538e-06, "loss": 0.169, "step": 104 }, { "epoch": 0.3143712574850299, "grad_norm": 3.02993094339149, "learning_rate": 9.402659248639749e-06, "loss": 0.175, "step": 105 }, { "epoch": 0.31736526946107785, "grad_norm": 3.0141022222679097, "learning_rate": 9.391464837010428e-06, "loss": 0.1889, "step": 106 }, { "epoch": 0.3203592814371258, "grad_norm": 3.070261726907226, "learning_rate": 9.380173294924661e-06, "loss": 0.1807, "step": 107 }, { "epoch": 0.32335329341317365, "grad_norm": 2.7083455123622118, "learning_rate": 9.368784872128877e-06, "loss": 0.1821, "step": 108 }, { "epoch": 0.3263473053892216, "grad_norm": 2.7929894788155325, "learning_rate": 9.357299820512305e-06, "loss": 0.1758, "step": 109 }, { "epoch": 0.32934131736526945, "grad_norm": 2.794970181481349, "learning_rate": 9.345718394101412e-06, "loss": 0.1868, "step": 110 }, { "epoch": 0.3323353293413174, "grad_norm": 2.7782986767818003, "learning_rate": 9.334040849054288e-06, "loss": 0.2063, "step": 111 }, { "epoch": 0.33532934131736525, "grad_norm": 2.772983977514824, "learning_rate": 9.322267443654974e-06, "loss": 0.1868, "step": 112 }, { "epoch": 0.3383233532934132, "grad_norm": 2.6793108608905003, "learning_rate": 9.310398438307747e-06, "loss": 0.2006, "step": 113 }, { "epoch": 0.3413173652694611, "grad_norm": 2.5870456933788617, "learning_rate": 9.29843409553137e-06, "loss": 0.1706, "step": 114 }, { "epoch": 0.344311377245509, "grad_norm": 2.657098741218333, "learning_rate": 9.286374679953278e-06, "loss": 0.1774, "step": 115 }, { "epoch": 0.3473053892215569, "grad_norm": 2.8014788285289343, "learning_rate": 9.274220458303727e-06, "loss": 0.1636, "step": 116 }, { "epoch": 0.3502994011976048, "grad_norm": 2.737175176673225, "learning_rate": 9.261971699409893e-06, "loss": 0.1928, "step": 117 }, { "epoch": 0.3532934131736527, "grad_norm": 2.896058241784804, "learning_rate": 9.249628674189928e-06, "loss": 0.1712, "step": 118 }, { "epoch": 0.3562874251497006, "grad_norm": 2.6776315920742215, "learning_rate": 9.237191655646972e-06, "loss": 0.1854, "step": 119 }, { "epoch": 0.3592814371257485, "grad_norm": 3.069754670176436, "learning_rate": 9.224660918863104e-06, "loss": 0.1772, "step": 120 }, { "epoch": 0.36227544910179643, "grad_norm": 2.7290412958038726, "learning_rate": 9.212036740993265e-06, "loss": 0.1721, "step": 121 }, { "epoch": 0.3652694610778443, "grad_norm": 2.8432182747219485, "learning_rate": 9.199319401259132e-06, "loss": 0.1686, "step": 122 }, { "epoch": 0.36826347305389223, "grad_norm": 2.744483776381965, "learning_rate": 9.186509180942928e-06, "loss": 0.1444, "step": 123 }, { "epoch": 0.3712574850299401, "grad_norm": 2.711445127914492, "learning_rate": 9.173606363381218e-06, "loss": 0.1793, "step": 124 }, { "epoch": 0.37425149700598803, "grad_norm": 3.049235163631386, "learning_rate": 9.16061123395863e-06, "loss": 0.1531, "step": 125 }, { "epoch": 0.3772455089820359, "grad_norm": 2.8204392474292024, "learning_rate": 9.147524080101543e-06, "loss": 0.1587, "step": 126 }, { "epoch": 0.38023952095808383, "grad_norm": 3.060861456087594, "learning_rate": 9.134345191271742e-06, "loss": 0.1851, "step": 127 }, { "epoch": 0.38323353293413176, "grad_norm": 3.1103842849453596, "learning_rate": 9.121074858959997e-06, "loss": 0.1925, "step": 128 }, { "epoch": 0.38622754491017963, "grad_norm": 3.002997950968262, "learning_rate": 9.107713376679634e-06, "loss": 0.1855, "step": 129 }, { "epoch": 0.38922155688622756, "grad_norm": 3.085124216691695, "learning_rate": 9.094261039960028e-06, "loss": 0.1746, "step": 130 }, { "epoch": 0.39221556886227543, "grad_norm": 3.202601411188671, "learning_rate": 9.08071814634008e-06, "loss": 0.1857, "step": 131 }, { "epoch": 0.39520958083832336, "grad_norm": 2.6915130570796246, "learning_rate": 9.067084995361623e-06, "loss": 0.1667, "step": 132 }, { "epoch": 0.39820359281437123, "grad_norm": 2.797219432729927, "learning_rate": 9.053361888562807e-06, "loss": 0.2109, "step": 133 }, { "epoch": 0.40119760479041916, "grad_norm": 2.7412287765355363, "learning_rate": 9.039549129471423e-06, "loss": 0.1735, "step": 134 }, { "epoch": 0.4041916167664671, "grad_norm": 2.717145693954402, "learning_rate": 9.025647023598196e-06, "loss": 0.1596, "step": 135 }, { "epoch": 0.40718562874251496, "grad_norm": 2.6104913806837353, "learning_rate": 9.011655878430018e-06, "loss": 0.1449, "step": 136 }, { "epoch": 0.4101796407185629, "grad_norm": 3.253811871474243, "learning_rate": 8.99757600342316e-06, "loss": 0.2367, "step": 137 }, { "epoch": 0.41317365269461076, "grad_norm": 2.935998224427179, "learning_rate": 8.983407709996415e-06, "loss": 0.1699, "step": 138 }, { "epoch": 0.4161676646706587, "grad_norm": 2.816170301043687, "learning_rate": 8.969151311524215e-06, "loss": 0.1436, "step": 139 }, { "epoch": 0.41916167664670656, "grad_norm": 2.8437624881056847, "learning_rate": 8.954807123329703e-06, "loss": 0.1806, "step": 140 }, { "epoch": 0.4221556886227545, "grad_norm": 2.647786327392162, "learning_rate": 8.940375462677758e-06, "loss": 0.1619, "step": 141 }, { "epoch": 0.4251497005988024, "grad_norm": 2.695052823694504, "learning_rate": 8.92585664876797e-06, "loss": 0.1891, "step": 142 }, { "epoch": 0.4281437125748503, "grad_norm": 2.4605022076232443, "learning_rate": 8.911251002727588e-06, "loss": 0.1538, "step": 143 }, { "epoch": 0.4311377245508982, "grad_norm": 2.4653470847923393, "learning_rate": 8.896558847604414e-06, "loss": 0.1633, "step": 144 }, { "epoch": 0.4341317365269461, "grad_norm": 2.781449524959415, "learning_rate": 8.881780508359661e-06, "loss": 0.1889, "step": 145 }, { "epoch": 0.437125748502994, "grad_norm": 2.86923188728662, "learning_rate": 8.86691631186076e-06, "loss": 0.1798, "step": 146 }, { "epoch": 0.44011976047904194, "grad_norm": 2.5930889590522783, "learning_rate": 8.851966586874138e-06, "loss": 0.1494, "step": 147 }, { "epoch": 0.4431137724550898, "grad_norm": 2.917867003727956, "learning_rate": 8.836931664057935e-06, "loss": 0.1982, "step": 148 }, { "epoch": 0.44610778443113774, "grad_norm": 2.888408420930644, "learning_rate": 8.821811875954705e-06, "loss": 0.1703, "step": 149 }, { "epoch": 0.4491017964071856, "grad_norm": 2.721603445504954, "learning_rate": 8.806607556984045e-06, "loss": 0.1796, "step": 150 }, { "epoch": 0.45209580838323354, "grad_norm": 2.5349542962323146, "learning_rate": 8.791319043435213e-06, "loss": 0.174, "step": 151 }, { "epoch": 0.4550898203592814, "grad_norm": 2.857863249019534, "learning_rate": 8.775946673459682e-06, "loss": 0.1793, "step": 152 }, { "epoch": 0.45808383233532934, "grad_norm": 2.8162466732714355, "learning_rate": 8.76049078706366e-06, "loss": 0.1605, "step": 153 }, { "epoch": 0.46107784431137727, "grad_norm": 2.845106041213913, "learning_rate": 8.744951726100572e-06, "loss": 0.1614, "step": 154 }, { "epoch": 0.46407185628742514, "grad_norm": 2.5149562685978117, "learning_rate": 8.729329834263503e-06, "loss": 0.1523, "step": 155 }, { "epoch": 0.46706586826347307, "grad_norm": 2.9767896458450798, "learning_rate": 8.713625457077585e-06, "loss": 0.2029, "step": 156 }, { "epoch": 0.47005988023952094, "grad_norm": 2.74853656493043, "learning_rate": 8.697838941892371e-06, "loss": 0.1791, "step": 157 }, { "epoch": 0.47305389221556887, "grad_norm": 2.4161340257276405, "learning_rate": 8.681970637874131e-06, "loss": 0.1893, "step": 158 }, { "epoch": 0.47604790419161674, "grad_norm": 2.848056681656514, "learning_rate": 8.666020895998154e-06, "loss": 0.1993, "step": 159 }, { "epoch": 0.47904191616766467, "grad_norm": 2.6084104277700795, "learning_rate": 8.64999006904096e-06, "loss": 0.1538, "step": 160 }, { "epoch": 0.4820359281437126, "grad_norm": 2.7448968538984033, "learning_rate": 8.63387851157252e-06, "loss": 0.1884, "step": 161 }, { "epoch": 0.48502994011976047, "grad_norm": 3.077105641815131, "learning_rate": 8.617686579948396e-06, "loss": 0.1751, "step": 162 }, { "epoch": 0.4880239520958084, "grad_norm": 2.863763769390867, "learning_rate": 8.60141463230187e-06, "loss": 0.1762, "step": 163 }, { "epoch": 0.49101796407185627, "grad_norm": 2.9028109341784054, "learning_rate": 8.585063028536015e-06, "loss": 0.1724, "step": 164 }, { "epoch": 0.4940119760479042, "grad_norm": 3.138374872761224, "learning_rate": 8.568632130315747e-06, "loss": 0.1902, "step": 165 }, { "epoch": 0.49700598802395207, "grad_norm": 2.5902246371320614, "learning_rate": 8.552122301059807e-06, "loss": 0.158, "step": 166 }, { "epoch": 0.5, "grad_norm": 2.5116201379888143, "learning_rate": 8.535533905932739e-06, "loss": 0.1532, "step": 167 }, { "epoch": 0.5029940119760479, "grad_norm": 2.6835359080980736, "learning_rate": 8.518867311836808e-06, "loss": 0.2012, "step": 168 }, { "epoch": 0.5059880239520959, "grad_norm": 2.4227847694986604, "learning_rate": 8.502122887403882e-06, "loss": 0.1432, "step": 169 }, { "epoch": 0.5089820359281437, "grad_norm": 2.627226416700839, "learning_rate": 8.485301002987285e-06, "loss": 0.1454, "step": 170 }, { "epoch": 0.5119760479041916, "grad_norm": 2.6326160270559, "learning_rate": 8.468402030653598e-06, "loss": 0.1961, "step": 171 }, { "epoch": 0.5149700598802395, "grad_norm": 2.4178292240615074, "learning_rate": 8.451426344174433e-06, "loss": 0.177, "step": 172 }, { "epoch": 0.5179640718562875, "grad_norm": 3.050105462563691, "learning_rate": 8.434374319018165e-06, "loss": 0.1735, "step": 173 }, { "epoch": 0.5209580838323353, "grad_norm": 2.668986492508351, "learning_rate": 8.417246332341638e-06, "loss": 0.1561, "step": 174 }, { "epoch": 0.5239520958083832, "grad_norm": 2.8687712382731, "learning_rate": 8.4000427629818e-06, "loss": 0.1703, "step": 175 }, { "epoch": 0.5269461077844312, "grad_norm": 2.531872064035627, "learning_rate": 8.382763991447344e-06, "loss": 0.1496, "step": 176 }, { "epoch": 0.5299401197604791, "grad_norm": 2.8413549758175454, "learning_rate": 8.365410399910287e-06, "loss": 0.1906, "step": 177 }, { "epoch": 0.5329341317365269, "grad_norm": 3.1790834234046357, "learning_rate": 8.347982372197515e-06, "loss": 0.1796, "step": 178 }, { "epoch": 0.5359281437125748, "grad_norm": 2.7770918354048915, "learning_rate": 8.33048029378229e-06, "loss": 0.1708, "step": 179 }, { "epoch": 0.5389221556886228, "grad_norm": 2.920244613732082, "learning_rate": 8.312904551775731e-06, "loss": 0.2158, "step": 180 }, { "epoch": 0.5419161676646707, "grad_norm": 2.8323551266066995, "learning_rate": 8.295255534918249e-06, "loss": 0.2168, "step": 181 }, { "epoch": 0.5449101796407185, "grad_norm": 3.2533647725826933, "learning_rate": 8.277533633570948e-06, "loss": 0.193, "step": 182 }, { "epoch": 0.5479041916167665, "grad_norm": 2.9053528038359624, "learning_rate": 8.25973923970699e-06, "loss": 0.185, "step": 183 }, { "epoch": 0.5508982035928144, "grad_norm": 2.494560172026245, "learning_rate": 8.241872746902934e-06, "loss": 0.1927, "step": 184 }, { "epoch": 0.5538922155688623, "grad_norm": 2.4807854323844403, "learning_rate": 8.223934550330015e-06, "loss": 0.1896, "step": 185 }, { "epoch": 0.5568862275449101, "grad_norm": 2.765426770671603, "learning_rate": 8.20592504674542e-06, "loss": 0.1913, "step": 186 }, { "epoch": 0.5598802395209581, "grad_norm": 3.0427909550145342, "learning_rate": 8.187844634483495e-06, "loss": 0.2162, "step": 187 }, { "epoch": 0.562874251497006, "grad_norm": 3.0322862177401984, "learning_rate": 8.16969371344696e-06, "loss": 0.199, "step": 188 }, { "epoch": 0.5658682634730539, "grad_norm": 2.650476458243997, "learning_rate": 8.151472685098037e-06, "loss": 0.189, "step": 189 }, { "epoch": 0.5688622754491018, "grad_norm": 2.7535488321549435, "learning_rate": 8.13318195244958e-06, "loss": 0.168, "step": 190 }, { "epoch": 0.5718562874251497, "grad_norm": 2.7352504990763604, "learning_rate": 8.114821920056177e-06, "loss": 0.1659, "step": 191 }, { "epoch": 0.5748502994011976, "grad_norm": 3.0240537107895427, "learning_rate": 8.096392994005177e-06, "loss": 0.2006, "step": 192 }, { "epoch": 0.5778443113772455, "grad_norm": 2.6226284682543266, "learning_rate": 8.077895581907719e-06, "loss": 0.1754, "step": 193 }, { "epoch": 0.5808383233532934, "grad_norm": 2.519683687852238, "learning_rate": 8.059330092889724e-06, "loss": 0.1839, "step": 194 }, { "epoch": 0.5838323353293413, "grad_norm": 2.922438264841633, "learning_rate": 8.040696937582833e-06, "loss": 0.2041, "step": 195 }, { "epoch": 0.5868263473053892, "grad_norm": 2.3277545637764017, "learning_rate": 8.021996528115335e-06, "loss": 0.1326, "step": 196 }, { "epoch": 0.5898203592814372, "grad_norm": 3.0570158963609555, "learning_rate": 8.003229278103044e-06, "loss": 0.1576, "step": 197 }, { "epoch": 0.592814371257485, "grad_norm": 2.8544491880461798, "learning_rate": 7.984395602640153e-06, "loss": 0.1739, "step": 198 }, { "epoch": 0.5958083832335329, "grad_norm": 2.754266546428125, "learning_rate": 7.96549591829006e-06, "loss": 0.1661, "step": 199 }, { "epoch": 0.5988023952095808, "grad_norm": 2.6571715186912277, "learning_rate": 7.946530643076138e-06, "loss": 0.1657, "step": 200 }, { "epoch": 0.5988023952095808, "eval_loss": 0.1959075927734375, "eval_runtime": 1.6269, "eval_samples_per_second": 33.192, "eval_steps_per_second": 8.605, "step": 200 }, { "epoch": 0.6017964071856288, "grad_norm": 2.2785579361111794, "learning_rate": 7.927500196472506e-06, "loss": 0.1725, "step": 201 }, { "epoch": 0.6047904191616766, "grad_norm": 2.832201857946005, "learning_rate": 7.908404999394747e-06, "loss": 0.1607, "step": 202 }, { "epoch": 0.6077844311377245, "grad_norm": 2.8427947822168482, "learning_rate": 7.889245474190588e-06, "loss": 0.1771, "step": 203 }, { "epoch": 0.6107784431137725, "grad_norm": 3.4247504484679454, "learning_rate": 7.870022044630569e-06, "loss": 0.2133, "step": 204 }, { "epoch": 0.6137724550898204, "grad_norm": 2.6649247959927824, "learning_rate": 7.85073513589867e-06, "loss": 0.1816, "step": 205 }, { "epoch": 0.6167664670658682, "grad_norm": 2.8808360877497408, "learning_rate": 7.831385174582901e-06, "loss": 0.161, "step": 206 }, { "epoch": 0.6197604790419161, "grad_norm": 2.500603411727198, "learning_rate": 7.81197258866587e-06, "loss": 0.1596, "step": 207 }, { "epoch": 0.6227544910179641, "grad_norm": 2.514237154341078, "learning_rate": 7.792497807515317e-06, "loss": 0.1568, "step": 208 }, { "epoch": 0.625748502994012, "grad_norm": 2.4435918400501007, "learning_rate": 7.772961261874615e-06, "loss": 0.1545, "step": 209 }, { "epoch": 0.6287425149700598, "grad_norm": 3.2497193874229593, "learning_rate": 7.75336338385325e-06, "loss": 0.1726, "step": 210 }, { "epoch": 0.6317365269461078, "grad_norm": 2.8600116890810225, "learning_rate": 7.733704606917248e-06, "loss": 0.2189, "step": 211 }, { "epoch": 0.6347305389221557, "grad_norm": 2.719660147370016, "learning_rate": 7.713985365879607e-06, "loss": 0.1479, "step": 212 }, { "epoch": 0.6377245508982036, "grad_norm": 2.953862115241413, "learning_rate": 7.694206096890667e-06, "loss": 0.2105, "step": 213 }, { "epoch": 0.6407185628742516, "grad_norm": 2.371989996791433, "learning_rate": 7.674367237428467e-06, "loss": 0.1555, "step": 214 }, { "epoch": 0.6437125748502994, "grad_norm": 2.697259925040803, "learning_rate": 7.654469226289068e-06, "loss": 0.1704, "step": 215 }, { "epoch": 0.6467065868263473, "grad_norm": 3.084083275334304, "learning_rate": 7.63451250357685e-06, "loss": 0.2055, "step": 216 }, { "epoch": 0.6497005988023952, "grad_norm": 2.6729869243465774, "learning_rate": 7.614497510694774e-06, "loss": 0.1644, "step": 217 }, { "epoch": 0.6526946107784432, "grad_norm": 2.734769897459554, "learning_rate": 7.5944246903346204e-06, "loss": 0.1781, "step": 218 }, { "epoch": 0.655688622754491, "grad_norm": 2.4051390656178633, "learning_rate": 7.574294486467204e-06, "loss": 0.1442, "step": 219 }, { "epoch": 0.6586826347305389, "grad_norm": 2.413408935611168, "learning_rate": 7.55410734433254e-06, "loss": 0.1565, "step": 220 }, { "epoch": 0.6616766467065869, "grad_norm": 2.7052091805621936, "learning_rate": 7.533863710430011e-06, "loss": 0.1811, "step": 221 }, { "epoch": 0.6646706586826348, "grad_norm": 2.055455991216137, "learning_rate": 7.513564032508484e-06, "loss": 0.1199, "step": 222 }, { "epoch": 0.6676646706586826, "grad_norm": 3.003971237409066, "learning_rate": 7.493208759556406e-06, "loss": 0.1884, "step": 223 }, { "epoch": 0.6706586826347305, "grad_norm": 2.698981420732048, "learning_rate": 7.472798341791877e-06, "loss": 0.1931, "step": 224 }, { "epoch": 0.6736526946107785, "grad_norm": 2.5618064203780007, "learning_rate": 7.452333230652688e-06, "loss": 0.1388, "step": 225 }, { "epoch": 0.6766467065868264, "grad_norm": 2.8523573365398187, "learning_rate": 7.431813878786343e-06, "loss": 0.1979, "step": 226 }, { "epoch": 0.6796407185628742, "grad_norm": 2.4954216930325432, "learning_rate": 7.4112407400400395e-06, "loss": 0.1237, "step": 227 }, { "epoch": 0.6826347305389222, "grad_norm": 2.3644435963229875, "learning_rate": 7.390614269450633e-06, "loss": 0.1361, "step": 228 }, { "epoch": 0.6856287425149701, "grad_norm": 2.494322911757774, "learning_rate": 7.369934923234577e-06, "loss": 0.1464, "step": 229 }, { "epoch": 0.688622754491018, "grad_norm": 2.8244432061967104, "learning_rate": 7.349203158777826e-06, "loss": 0.1522, "step": 230 }, { "epoch": 0.6916167664670658, "grad_norm": 2.4038052102758156, "learning_rate": 7.32841943462572e-06, "loss": 0.1614, "step": 231 }, { "epoch": 0.6946107784431138, "grad_norm": 2.8959123165307927, "learning_rate": 7.3075842104728445e-06, "loss": 0.1805, "step": 232 }, { "epoch": 0.6976047904191617, "grad_norm": 2.739484557902547, "learning_rate": 7.286697947152868e-06, "loss": 0.1814, "step": 233 }, { "epoch": 0.7005988023952096, "grad_norm": 2.2537252037236484, "learning_rate": 7.265761106628338e-06, "loss": 0.1515, "step": 234 }, { "epoch": 0.7035928143712575, "grad_norm": 2.774788912966986, "learning_rate": 7.244774151980466e-06, "loss": 0.1638, "step": 235 }, { "epoch": 0.7065868263473054, "grad_norm": 2.959559796396983, "learning_rate": 7.223737547398898e-06, "loss": 0.1625, "step": 236 }, { "epoch": 0.7095808383233533, "grad_norm": 2.5367908669042567, "learning_rate": 7.20265175817143e-06, "loss": 0.1558, "step": 237 }, { "epoch": 0.7125748502994012, "grad_norm": 3.1986749391400893, "learning_rate": 7.181517250673729e-06, "loss": 0.2267, "step": 238 }, { "epoch": 0.7155688622754491, "grad_norm": 2.8169158835159576, "learning_rate": 7.1603344923590065e-06, "loss": 0.1756, "step": 239 }, { "epoch": 0.718562874251497, "grad_norm": 2.999169784220672, "learning_rate": 7.139103951747694e-06, "loss": 0.211, "step": 240 }, { "epoch": 0.7215568862275449, "grad_norm": 2.723555191873519, "learning_rate": 7.1178260984170675e-06, "loss": 0.1627, "step": 241 }, { "epoch": 0.7245508982035929, "grad_norm": 2.796852647624867, "learning_rate": 7.0965014029908654e-06, "loss": 0.1472, "step": 242 }, { "epoch": 0.7275449101796407, "grad_norm": 2.5475243452133904, "learning_rate": 7.075130337128883e-06, "loss": 0.2163, "step": 243 }, { "epoch": 0.7305389221556886, "grad_norm": 3.027968305694753, "learning_rate": 7.053713373516538e-06, "loss": 0.2292, "step": 244 }, { "epoch": 0.7335329341317365, "grad_norm": 2.7557987193144533, "learning_rate": 7.03225098585441e-06, "loss": 0.2046, "step": 245 }, { "epoch": 0.7365269461077845, "grad_norm": 2.723900723130319, "learning_rate": 7.0107436488477694e-06, "loss": 0.2052, "step": 246 }, { "epoch": 0.7395209580838323, "grad_norm": 2.794584346622902, "learning_rate": 6.989191838196083e-06, "loss": 0.1796, "step": 247 }, { "epoch": 0.7425149700598802, "grad_norm": 2.383042322453841, "learning_rate": 6.9675960305824785e-06, "loss": 0.1507, "step": 248 }, { "epoch": 0.7455089820359282, "grad_norm": 2.975231770546583, "learning_rate": 6.945956703663212e-06, "loss": 0.1886, "step": 249 }, { "epoch": 0.7485029940119761, "grad_norm": 2.484905447167976, "learning_rate": 6.9242743360570985e-06, "loss": 0.1813, "step": 250 }, { "epoch": 0.7514970059880239, "grad_norm": 2.568048443813201, "learning_rate": 6.9025494073349284e-06, "loss": 0.1821, "step": 251 }, { "epoch": 0.7544910179640718, "grad_norm": 2.5399177827130877, "learning_rate": 6.880782398008862e-06, "loss": 0.1847, "step": 252 }, { "epoch": 0.7574850299401198, "grad_norm": 2.393932528101437, "learning_rate": 6.858973789521792e-06, "loss": 0.1497, "step": 253 }, { "epoch": 0.7604790419161677, "grad_norm": 2.5882615611863917, "learning_rate": 6.837124064236709e-06, "loss": 0.17, "step": 254 }, { "epoch": 0.7634730538922155, "grad_norm": 2.2446612560830217, "learning_rate": 6.815233705426019e-06, "loss": 0.1501, "step": 255 }, { "epoch": 0.7664670658682635, "grad_norm": 2.4879001226303488, "learning_rate": 6.7933031972608644e-06, "loss": 0.1658, "step": 256 }, { "epoch": 0.7694610778443114, "grad_norm": 2.880322385182476, "learning_rate": 6.771333024800411e-06, "loss": 0.191, "step": 257 }, { "epoch": 0.7724550898203593, "grad_norm": 2.949041398439932, "learning_rate": 6.74932367398112e-06, "loss": 0.1842, "step": 258 }, { "epoch": 0.7754491017964071, "grad_norm": 2.310131123108099, "learning_rate": 6.727275631605996e-06, "loss": 0.1415, "step": 259 }, { "epoch": 0.7784431137724551, "grad_norm": 2.73569034130157, "learning_rate": 6.70518938533383e-06, "loss": 0.1801, "step": 260 }, { "epoch": 0.781437125748503, "grad_norm": 2.4270887890327697, "learning_rate": 6.683065423668403e-06, "loss": 0.1403, "step": 261 }, { "epoch": 0.7844311377245509, "grad_norm": 2.7083201342415797, "learning_rate": 6.660904235947687e-06, "loss": 0.1789, "step": 262 }, { "epoch": 0.7874251497005988, "grad_norm": 2.6124636950203066, "learning_rate": 6.638706312333018e-06, "loss": 0.1584, "step": 263 }, { "epoch": 0.7904191616766467, "grad_norm": 2.996211442405573, "learning_rate": 6.61647214379826e-06, "loss": 0.1803, "step": 264 }, { "epoch": 0.7934131736526946, "grad_norm": 3.3322920091856325, "learning_rate": 6.594202222118941e-06, "loss": 0.2015, "step": 265 }, { "epoch": 0.7964071856287425, "grad_norm": 2.833161048568437, "learning_rate": 6.571897039861377e-06, "loss": 0.1598, "step": 266 }, { "epoch": 0.7994011976047904, "grad_norm": 2.615993057489343, "learning_rate": 6.549557090371775e-06, "loss": 0.1975, "step": 267 }, { "epoch": 0.8023952095808383, "grad_norm": 2.3460557645107945, "learning_rate": 6.527182867765333e-06, "loss": 0.1309, "step": 268 }, { "epoch": 0.8053892215568862, "grad_norm": 3.003914320216377, "learning_rate": 6.504774866915291e-06, "loss": 0.2026, "step": 269 }, { "epoch": 0.8083832335329342, "grad_norm": 2.5300334464065894, "learning_rate": 6.482333583442002e-06, "loss": 0.1609, "step": 270 }, { "epoch": 0.811377245508982, "grad_norm": 2.8178813828603113, "learning_rate": 6.459859513701967e-06, "loss": 0.1775, "step": 271 }, { "epoch": 0.8143712574850299, "grad_norm": 3.314644269270267, "learning_rate": 6.437353154776848e-06, "loss": 0.1698, "step": 272 }, { "epoch": 0.8173652694610778, "grad_norm": 2.655361531038752, "learning_rate": 6.414815004462483e-06, "loss": 0.1486, "step": 273 }, { "epoch": 0.8203592814371258, "grad_norm": 2.534523473700059, "learning_rate": 6.3922455612578715e-06, "loss": 0.1943, "step": 274 }, { "epoch": 0.8233532934131736, "grad_norm": 2.6920816152952423, "learning_rate": 6.369645324354149e-06, "loss": 0.1428, "step": 275 }, { "epoch": 0.8263473053892215, "grad_norm": 3.0022716384776755, "learning_rate": 6.3470147936235485e-06, "loss": 0.2133, "step": 276 }, { "epoch": 0.8293413173652695, "grad_norm": 2.1712322145261065, "learning_rate": 6.3243544696083355e-06, "loss": 0.1511, "step": 277 }, { "epoch": 0.8323353293413174, "grad_norm": 3.0356816941732117, "learning_rate": 6.301664853509755e-06, "loss": 0.2042, "step": 278 }, { "epoch": 0.8353293413173652, "grad_norm": 2.89577704962357, "learning_rate": 6.278946447176924e-06, "loss": 0.1473, "step": 279 }, { "epoch": 0.8383233532934131, "grad_norm": 2.6686103360284212, "learning_rate": 6.256199753095745e-06, "loss": 0.1725, "step": 280 }, { "epoch": 0.8413173652694611, "grad_norm": 2.4109236432706225, "learning_rate": 6.233425274377793e-06, "loss": 0.1537, "step": 281 }, { "epoch": 0.844311377245509, "grad_norm": 2.7129281572914627, "learning_rate": 6.21062351474918e-06, "loss": 0.1574, "step": 282 }, { "epoch": 0.8473053892215568, "grad_norm": 2.6272841854370155, "learning_rate": 6.18779497853942e-06, "loss": 0.1641, "step": 283 }, { "epoch": 0.8502994011976048, "grad_norm": 2.636815954958081, "learning_rate": 6.164940170670266e-06, "loss": 0.1987, "step": 284 }, { "epoch": 0.8532934131736527, "grad_norm": 2.614745188654968, "learning_rate": 6.142059596644557e-06, "loss": 0.1556, "step": 285 }, { "epoch": 0.8562874251497006, "grad_norm": 2.7095080589549205, "learning_rate": 6.11915376253502e-06, "loss": 0.1425, "step": 286 }, { "epoch": 0.8592814371257484, "grad_norm": 2.6124991630484034, "learning_rate": 6.096223174973091e-06, "loss": 0.1655, "step": 287 }, { "epoch": 0.8622754491017964, "grad_norm": 2.530336713216177, "learning_rate": 6.073268341137694e-06, "loss": 0.1371, "step": 288 }, { "epoch": 0.8652694610778443, "grad_norm": 2.7063770384141375, "learning_rate": 6.050289768744042e-06, "loss": 0.1692, "step": 289 }, { "epoch": 0.8682634730538922, "grad_norm": 2.7009333885925, "learning_rate": 6.0272879660323936e-06, "loss": 0.1767, "step": 290 }, { "epoch": 0.8712574850299402, "grad_norm": 2.6785196474751567, "learning_rate": 6.004263441756815e-06, "loss": 0.1737, "step": 291 }, { "epoch": 0.874251497005988, "grad_norm": 2.9974659375592063, "learning_rate": 5.98121670517393e-06, "loss": 0.1866, "step": 292 }, { "epoch": 0.8772455089820359, "grad_norm": 2.494762988918377, "learning_rate": 5.958148266031654e-06, "loss": 0.1675, "step": 293 }, { "epoch": 0.8802395209580839, "grad_norm": 2.5097901544383214, "learning_rate": 5.935058634557917e-06, "loss": 0.1426, "step": 294 }, { "epoch": 0.8832335329341318, "grad_norm": 2.3739210445513956, "learning_rate": 5.911948321449384e-06, "loss": 0.1574, "step": 295 }, { "epoch": 0.8862275449101796, "grad_norm": 3.095819586546114, "learning_rate": 5.8888178378601565e-06, "loss": 0.1806, "step": 296 }, { "epoch": 0.8892215568862275, "grad_norm": 2.772749539806525, "learning_rate": 5.865667695390468e-06, "loss": 0.1764, "step": 297 }, { "epoch": 0.8922155688622755, "grad_norm": 2.413830905353264, "learning_rate": 5.842498406075363e-06, "loss": 0.1361, "step": 298 }, { "epoch": 0.8952095808383234, "grad_norm": 2.3084168214112766, "learning_rate": 5.819310482373381e-06, "loss": 0.1203, "step": 299 }, { "epoch": 0.8982035928143712, "grad_norm": 2.746015751477771, "learning_rate": 5.796104437155213e-06, "loss": 0.1839, "step": 300 }, { "epoch": 0.9011976047904192, "grad_norm": 2.61072507221329, "learning_rate": 5.772880783692363e-06, "loss": 0.1456, "step": 301 }, { "epoch": 0.9041916167664671, "grad_norm": 2.8562495227983287, "learning_rate": 5.749640035645798e-06, "loss": 0.1843, "step": 302 }, { "epoch": 0.907185628742515, "grad_norm": 2.4424774804085607, "learning_rate": 5.726382707054578e-06, "loss": 0.1356, "step": 303 }, { "epoch": 0.9101796407185628, "grad_norm": 2.752853667987109, "learning_rate": 5.703109312324493e-06, "loss": 0.1746, "step": 304 }, { "epoch": 0.9131736526946108, "grad_norm": 2.828030440659521, "learning_rate": 5.679820366216684e-06, "loss": 0.191, "step": 305 }, { "epoch": 0.9161676646706587, "grad_norm": 2.222682756404927, "learning_rate": 5.656516383836263e-06, "loss": 0.1401, "step": 306 }, { "epoch": 0.9191616766467066, "grad_norm": 2.8191638429065593, "learning_rate": 5.6331978806209044e-06, "loss": 0.2005, "step": 307 }, { "epoch": 0.9221556886227545, "grad_norm": 2.638186883455561, "learning_rate": 5.609865372329461e-06, "loss": 0.1552, "step": 308 }, { "epoch": 0.9251497005988024, "grad_norm": 2.833598088587227, "learning_rate": 5.586519375030549e-06, "loss": 0.1798, "step": 309 }, { "epoch": 0.9281437125748503, "grad_norm": 2.6511518693876353, "learning_rate": 5.5631604050911354e-06, "loss": 0.1589, "step": 310 }, { "epoch": 0.9311377245508982, "grad_norm": 2.776585660423919, "learning_rate": 5.539788979165115e-06, "loss": 0.1749, "step": 311 }, { "epoch": 0.9341317365269461, "grad_norm": 2.166880149257365, "learning_rate": 5.516405614181883e-06, "loss": 0.1533, "step": 312 }, { "epoch": 0.937125748502994, "grad_norm": 2.349994637773294, "learning_rate": 5.4930108273349034e-06, "loss": 0.1422, "step": 313 }, { "epoch": 0.9401197604790419, "grad_norm": 2.452503407557057, "learning_rate": 5.4696051360702725e-06, "loss": 0.1622, "step": 314 }, { "epoch": 0.9431137724550899, "grad_norm": 2.933677937538358, "learning_rate": 5.446189058075265e-06, "loss": 0.1889, "step": 315 }, { "epoch": 0.9461077844311377, "grad_norm": 2.8496036384482912, "learning_rate": 5.4227631112668955e-06, "loss": 0.1883, "step": 316 }, { "epoch": 0.9491017964071856, "grad_norm": 2.5502697583568605, "learning_rate": 5.39932781378045e-06, "loss": 0.1425, "step": 317 }, { "epoch": 0.9520958083832335, "grad_norm": 2.8636194867379907, "learning_rate": 5.375883683958041e-06, "loss": 0.2112, "step": 318 }, { "epoch": 0.9550898203592815, "grad_norm": 2.719023379936637, "learning_rate": 5.3524312403371255e-06, "loss": 0.1569, "step": 319 }, { "epoch": 0.9580838323353293, "grad_norm": 2.645226897587009, "learning_rate": 5.328971001639054e-06, "loss": 0.1511, "step": 320 }, { "epoch": 0.9610778443113772, "grad_norm": 3.0663542716752454, "learning_rate": 5.3055034867575825e-06, "loss": 0.2008, "step": 321 }, { "epoch": 0.9640718562874252, "grad_norm": 2.9422623971931863, "learning_rate": 5.282029214747404e-06, "loss": 0.1827, "step": 322 }, { "epoch": 0.9670658682634731, "grad_norm": 2.800181227219654, "learning_rate": 5.258548704812667e-06, "loss": 0.1724, "step": 323 }, { "epoch": 0.9700598802395209, "grad_norm": 2.9426003516662393, "learning_rate": 5.235062476295488e-06, "loss": 0.1851, "step": 324 }, { "epoch": 0.9730538922155688, "grad_norm": 2.7141097912850154, "learning_rate": 5.211571048664469e-06, "loss": 0.1637, "step": 325 }, { "epoch": 0.9760479041916168, "grad_norm": 2.467798821025675, "learning_rate": 5.188074941503203e-06, "loss": 0.1563, "step": 326 }, { "epoch": 0.9790419161676647, "grad_norm": 2.7809808957709423, "learning_rate": 5.164574674498788e-06, "loss": 0.174, "step": 327 }, { "epoch": 0.9820359281437125, "grad_norm": 2.566093951302036, "learning_rate": 5.141070767430331e-06, "loss": 0.1523, "step": 328 }, { "epoch": 0.9850299401197605, "grad_norm": 2.661086296799041, "learning_rate": 5.117563740157444e-06, "loss": 0.1709, "step": 329 }, { "epoch": 0.9880239520958084, "grad_norm": 2.631833356533506, "learning_rate": 5.094054112608758e-06, "loss": 0.1636, "step": 330 }, { "epoch": 0.9910179640718563, "grad_norm": 2.6521546529671336, "learning_rate": 5.070542404770413e-06, "loss": 0.1573, "step": 331 }, { "epoch": 0.9940119760479041, "grad_norm": 2.5016212674443215, "learning_rate": 5.047029136674563e-06, "loss": 0.1411, "step": 332 }, { "epoch": 0.9970059880239521, "grad_norm": 3.2602846624984214, "learning_rate": 5.023514828387868e-06, "loss": 0.2048, "step": 333 }, { "epoch": 1.0, "grad_norm": 2.180468424870148, "learning_rate": 5e-06, "loss": 0.0839, "step": 334 }, { "epoch": 1.0029940119760479, "grad_norm": 2.11704179847878, "learning_rate": 4.976485171612134e-06, "loss": 0.0804, "step": 335 }, { "epoch": 1.0059880239520957, "grad_norm": 2.3922717281251216, "learning_rate": 4.95297086332544e-06, "loss": 0.0992, "step": 336 }, { "epoch": 1.0089820359281436, "grad_norm": 2.1858749179370687, "learning_rate": 4.9294575952295896e-06, "loss": 0.0926, "step": 337 }, { "epoch": 1.0119760479041917, "grad_norm": 2.2962404942602594, "learning_rate": 4.905945887391242e-06, "loss": 0.0893, "step": 338 }, { "epoch": 1.0149700598802396, "grad_norm": 1.981213692508198, "learning_rate": 4.882436259842556e-06, "loss": 0.06, "step": 339 }, { "epoch": 1.0179640718562875, "grad_norm": 2.0358487465964252, "learning_rate": 4.858929232569671e-06, "loss": 0.0739, "step": 340 }, { "epoch": 1.0209580838323353, "grad_norm": 2.7452516193739345, "learning_rate": 4.835425325501214e-06, "loss": 0.1091, "step": 341 }, { "epoch": 1.0239520958083832, "grad_norm": 2.724907707466572, "learning_rate": 4.811925058496799e-06, "loss": 0.089, "step": 342 }, { "epoch": 1.026946107784431, "grad_norm": 2.207732585878351, "learning_rate": 4.788428951335534e-06, "loss": 0.0813, "step": 343 }, { "epoch": 1.029940119760479, "grad_norm": 2.320815826153711, "learning_rate": 4.7649375237045135e-06, "loss": 0.0927, "step": 344 }, { "epoch": 1.032934131736527, "grad_norm": 2.206642445779226, "learning_rate": 4.741451295187333e-06, "loss": 0.0716, "step": 345 }, { "epoch": 1.035928143712575, "grad_norm": 2.914497860494145, "learning_rate": 4.717970785252596e-06, "loss": 0.0988, "step": 346 }, { "epoch": 1.0389221556886228, "grad_norm": 2.872306850473374, "learning_rate": 4.694496513242418e-06, "loss": 0.1062, "step": 347 }, { "epoch": 1.0419161676646707, "grad_norm": 2.5109654606188414, "learning_rate": 4.671028998360947e-06, "loss": 0.0771, "step": 348 }, { "epoch": 1.0449101796407185, "grad_norm": 2.9785984398896654, "learning_rate": 4.647568759662876e-06, "loss": 0.0677, "step": 349 }, { "epoch": 1.0479041916167664, "grad_norm": 2.682794280568352, "learning_rate": 4.624116316041962e-06, "loss": 0.0799, "step": 350 }, { "epoch": 1.0508982035928143, "grad_norm": 2.3084612675935605, "learning_rate": 4.600672186219551e-06, "loss": 0.0868, "step": 351 }, { "epoch": 1.0538922155688624, "grad_norm": 3.15640860150235, "learning_rate": 4.5772368887331044e-06, "loss": 0.0851, "step": 352 }, { "epoch": 1.0568862275449102, "grad_norm": 3.0262877766504888, "learning_rate": 4.553810941924735e-06, "loss": 0.1323, "step": 353 }, { "epoch": 1.0598802395209581, "grad_norm": 2.4780860692379707, "learning_rate": 4.530394863929728e-06, "loss": 0.1001, "step": 354 }, { "epoch": 1.062874251497006, "grad_norm": 2.5700940473207026, "learning_rate": 4.506989172665097e-06, "loss": 0.1001, "step": 355 }, { "epoch": 1.0658682634730539, "grad_norm": 2.3946324226062776, "learning_rate": 4.483594385818119e-06, "loss": 0.0601, "step": 356 }, { "epoch": 1.0688622754491017, "grad_norm": 3.0554636137690405, "learning_rate": 4.460211020834887e-06, "loss": 0.0876, "step": 357 }, { "epoch": 1.0718562874251496, "grad_norm": 2.480224137398899, "learning_rate": 4.436839594908866e-06, "loss": 0.0936, "step": 358 }, { "epoch": 1.0748502994011977, "grad_norm": 2.201002228990114, "learning_rate": 4.4134806249694514e-06, "loss": 0.0855, "step": 359 }, { "epoch": 1.0778443113772456, "grad_norm": 3.0981693722191057, "learning_rate": 4.39013462767054e-06, "loss": 0.1181, "step": 360 }, { "epoch": 1.0808383233532934, "grad_norm": 2.3189000403265667, "learning_rate": 4.366802119379098e-06, "loss": 0.0844, "step": 361 }, { "epoch": 1.0838323353293413, "grad_norm": 2.535504674203273, "learning_rate": 4.34348361616374e-06, "loss": 0.0863, "step": 362 }, { "epoch": 1.0868263473053892, "grad_norm": 2.8684470918440876, "learning_rate": 4.3201796337833165e-06, "loss": 0.0863, "step": 363 }, { "epoch": 1.089820359281437, "grad_norm": 2.4031264421179124, "learning_rate": 4.29689068767551e-06, "loss": 0.0713, "step": 364 }, { "epoch": 1.092814371257485, "grad_norm": 2.645676311381572, "learning_rate": 4.273617292945425e-06, "loss": 0.0886, "step": 365 }, { "epoch": 1.095808383233533, "grad_norm": 2.3800478124539977, "learning_rate": 4.250359964354203e-06, "loss": 0.0839, "step": 366 }, { "epoch": 1.098802395209581, "grad_norm": 2.253648439114172, "learning_rate": 4.227119216307637e-06, "loss": 0.0681, "step": 367 }, { "epoch": 1.1017964071856288, "grad_norm": 2.5878454405633815, "learning_rate": 4.203895562844789e-06, "loss": 0.0868, "step": 368 }, { "epoch": 1.1047904191616766, "grad_norm": 2.684883969540195, "learning_rate": 4.18068951762662e-06, "loss": 0.0924, "step": 369 }, { "epoch": 1.1077844311377245, "grad_norm": 2.3997775927841247, "learning_rate": 4.157501593924638e-06, "loss": 0.0829, "step": 370 }, { "epoch": 1.1107784431137724, "grad_norm": 2.704465528436201, "learning_rate": 4.134332304609533e-06, "loss": 0.1158, "step": 371 }, { "epoch": 1.1137724550898203, "grad_norm": 2.149869817140851, "learning_rate": 4.111182162139844e-06, "loss": 0.0773, "step": 372 }, { "epoch": 1.1167664670658684, "grad_norm": 2.4883562158610024, "learning_rate": 4.088051678550617e-06, "loss": 0.072, "step": 373 }, { "epoch": 1.1197604790419162, "grad_norm": 2.4070533782720047, "learning_rate": 4.064941365442084e-06, "loss": 0.0889, "step": 374 }, { "epoch": 1.122754491017964, "grad_norm": 3.2001643962693054, "learning_rate": 4.041851733968348e-06, "loss": 0.1108, "step": 375 }, { "epoch": 1.125748502994012, "grad_norm": 2.6670371718723116, "learning_rate": 4.018783294826071e-06, "loss": 0.0973, "step": 376 }, { "epoch": 1.1287425149700598, "grad_norm": 3.0787303585914656, "learning_rate": 3.995736558243186e-06, "loss": 0.0842, "step": 377 }, { "epoch": 1.1317365269461077, "grad_norm": 2.494954356724727, "learning_rate": 3.972712033967608e-06, "loss": 0.1104, "step": 378 }, { "epoch": 1.1347305389221556, "grad_norm": 2.7791965125002394, "learning_rate": 3.949710231255961e-06, "loss": 0.1052, "step": 379 }, { "epoch": 1.1377245508982037, "grad_norm": 2.724203731214569, "learning_rate": 3.926731658862307e-06, "loss": 0.0967, "step": 380 }, { "epoch": 1.1407185628742516, "grad_norm": 2.1978317620196735, "learning_rate": 3.903776825026912e-06, "loss": 0.0874, "step": 381 }, { "epoch": 1.1437125748502994, "grad_norm": 2.3334907847998454, "learning_rate": 3.8808462374649805e-06, "loss": 0.1077, "step": 382 }, { "epoch": 1.1467065868263473, "grad_norm": 2.3575104399649356, "learning_rate": 3.857940403355444e-06, "loss": 0.0747, "step": 383 }, { "epoch": 1.1497005988023952, "grad_norm": 2.5714185503718006, "learning_rate": 3.8350598293297345e-06, "loss": 0.127, "step": 384 }, { "epoch": 1.152694610778443, "grad_norm": 2.7114187668028413, "learning_rate": 3.8122050214605822e-06, "loss": 0.1014, "step": 385 }, { "epoch": 1.1556886227544911, "grad_norm": 2.706453939514744, "learning_rate": 3.7893764852508207e-06, "loss": 0.1251, "step": 386 }, { "epoch": 1.158682634730539, "grad_norm": 2.1095877714192635, "learning_rate": 3.766574725622208e-06, "loss": 0.0765, "step": 387 }, { "epoch": 1.1616766467065869, "grad_norm": 2.29567697360027, "learning_rate": 3.7438002469042567e-06, "loss": 0.0831, "step": 388 }, { "epoch": 1.1646706586826348, "grad_norm": 2.3865867053126584, "learning_rate": 3.721053552823078e-06, "loss": 0.0963, "step": 389 }, { "epoch": 1.1676646706586826, "grad_norm": 2.4524237984264943, "learning_rate": 3.698335146490246e-06, "loss": 0.0907, "step": 390 }, { "epoch": 1.1706586826347305, "grad_norm": 2.665037011436698, "learning_rate": 3.675645530391665e-06, "loss": 0.0783, "step": 391 }, { "epoch": 1.1736526946107784, "grad_norm": 2.6519498185177204, "learning_rate": 3.652985206376455e-06, "loss": 0.0836, "step": 392 }, { "epoch": 1.1766467065868262, "grad_norm": 2.5025139992637957, "learning_rate": 3.630354675645853e-06, "loss": 0.0935, "step": 393 }, { "epoch": 1.1796407185628743, "grad_norm": 2.64857904915377, "learning_rate": 3.6077544387421293e-06, "loss": 0.0907, "step": 394 }, { "epoch": 1.1826347305389222, "grad_norm": 2.0134593610315896, "learning_rate": 3.5851849955375177e-06, "loss": 0.0647, "step": 395 }, { "epoch": 1.18562874251497, "grad_norm": 2.404541109546884, "learning_rate": 3.5626468452231534e-06, "loss": 0.0806, "step": 396 }, { "epoch": 1.188622754491018, "grad_norm": 2.131224195183676, "learning_rate": 3.540140486298035e-06, "loss": 0.0756, "step": 397 }, { "epoch": 1.1916167664670658, "grad_norm": 2.422349384630172, "learning_rate": 3.517666416557999e-06, "loss": 0.1037, "step": 398 }, { "epoch": 1.1946107784431137, "grad_norm": 2.414313700533083, "learning_rate": 3.495225133084712e-06, "loss": 0.079, "step": 399 }, { "epoch": 1.1976047904191618, "grad_norm": 2.3621380019917595, "learning_rate": 3.472817132234669e-06, "loss": 0.0877, "step": 400 }, { "epoch": 1.1976047904191618, "eval_loss": 0.19929930567741394, "eval_runtime": 1.6087, "eval_samples_per_second": 33.567, "eval_steps_per_second": 8.703, "step": 400 }, { "epoch": 1.2005988023952097, "grad_norm": 2.335009542772763, "learning_rate": 3.4504429096282246e-06, "loss": 0.0897, "step": 401 }, { "epoch": 1.2035928143712575, "grad_norm": 2.363963216400376, "learning_rate": 3.428102960138625e-06, "loss": 0.0966, "step": 402 }, { "epoch": 1.2065868263473054, "grad_norm": 2.680631887268738, "learning_rate": 3.405797777881059e-06, "loss": 0.097, "step": 403 }, { "epoch": 1.2095808383233533, "grad_norm": 2.2945767476114196, "learning_rate": 3.3835278562017405e-06, "loss": 0.0725, "step": 404 }, { "epoch": 1.2125748502994012, "grad_norm": 2.170251725128939, "learning_rate": 3.3612936876669834e-06, "loss": 0.0785, "step": 405 }, { "epoch": 1.215568862275449, "grad_norm": 2.3884948794863585, "learning_rate": 3.3390957640523147e-06, "loss": 0.1019, "step": 406 }, { "epoch": 1.218562874251497, "grad_norm": 2.178361270723467, "learning_rate": 3.3169345763315986e-06, "loss": 0.0818, "step": 407 }, { "epoch": 1.221556886227545, "grad_norm": 2.1769370885401575, "learning_rate": 3.29481061466617e-06, "loss": 0.0936, "step": 408 }, { "epoch": 1.2245508982035929, "grad_norm": 2.826236240888856, "learning_rate": 3.2727243683940045e-06, "loss": 0.1029, "step": 409 }, { "epoch": 1.2275449101796407, "grad_norm": 2.440072520827904, "learning_rate": 3.2506763260188824e-06, "loss": 0.0796, "step": 410 }, { "epoch": 1.2305389221556886, "grad_norm": 2.3076849351154896, "learning_rate": 3.2286669751995905e-06, "loss": 0.0756, "step": 411 }, { "epoch": 1.2335329341317365, "grad_norm": 2.8857553361856842, "learning_rate": 3.2066968027391377e-06, "loss": 0.0863, "step": 412 }, { "epoch": 1.2365269461077844, "grad_norm": 2.081559403529547, "learning_rate": 3.1847662945739833e-06, "loss": 0.0767, "step": 413 }, { "epoch": 1.2395209580838324, "grad_norm": 2.1243064149395816, "learning_rate": 3.1628759357632943e-06, "loss": 0.0739, "step": 414 }, { "epoch": 1.2425149700598803, "grad_norm": 2.667566893610402, "learning_rate": 3.1410262104782086e-06, "loss": 0.0786, "step": 415 }, { "epoch": 1.2455089820359282, "grad_norm": 2.555569731896872, "learning_rate": 3.119217601991139e-06, "loss": 0.0985, "step": 416 }, { "epoch": 1.248502994011976, "grad_norm": 2.717074046557265, "learning_rate": 3.0974505926650724e-06, "loss": 0.0885, "step": 417 }, { "epoch": 1.251497005988024, "grad_norm": 2.1572924016136783, "learning_rate": 3.0757256639429027e-06, "loss": 0.0812, "step": 418 }, { "epoch": 1.2544910179640718, "grad_norm": 2.321178065652392, "learning_rate": 3.0540432963367907e-06, "loss": 0.0876, "step": 419 }, { "epoch": 1.2574850299401197, "grad_norm": 2.317098965475441, "learning_rate": 3.032403969417523e-06, "loss": 0.075, "step": 420 }, { "epoch": 1.2604790419161676, "grad_norm": 2.385065665880118, "learning_rate": 3.010808161803917e-06, "loss": 0.0935, "step": 421 }, { "epoch": 1.2634730538922156, "grad_norm": 2.5176974480912535, "learning_rate": 2.9892563511522305e-06, "loss": 0.1016, "step": 422 }, { "epoch": 1.2664670658682635, "grad_norm": 2.1759737090214215, "learning_rate": 2.9677490141455915e-06, "loss": 0.0897, "step": 423 }, { "epoch": 1.2694610778443114, "grad_norm": 2.551532457720297, "learning_rate": 2.946286626483463e-06, "loss": 0.1182, "step": 424 }, { "epoch": 1.2724550898203593, "grad_norm": 2.3799254702321644, "learning_rate": 2.924869662871117e-06, "loss": 0.0785, "step": 425 }, { "epoch": 1.2754491017964071, "grad_norm": 2.301519716404854, "learning_rate": 2.903498597009136e-06, "loss": 0.1003, "step": 426 }, { "epoch": 1.278443113772455, "grad_norm": 2.3178185162438214, "learning_rate": 2.8821739015829338e-06, "loss": 0.0781, "step": 427 }, { "epoch": 1.281437125748503, "grad_norm": 1.9544993926124197, "learning_rate": 2.8608960482523058e-06, "loss": 0.0651, "step": 428 }, { "epoch": 1.284431137724551, "grad_norm": 2.332908829968547, "learning_rate": 2.839665507640992e-06, "loss": 0.078, "step": 429 }, { "epoch": 1.2874251497005988, "grad_norm": 2.587223088081551, "learning_rate": 2.818482749326272e-06, "loss": 0.0879, "step": 430 }, { "epoch": 1.2904191616766467, "grad_norm": 2.5433992667352743, "learning_rate": 2.797348241828569e-06, "loss": 0.0864, "step": 431 }, { "epoch": 1.2934131736526946, "grad_norm": 2.3100890694349903, "learning_rate": 2.776262452601104e-06, "loss": 0.0865, "step": 432 }, { "epoch": 1.2964071856287425, "grad_norm": 2.502114053723801, "learning_rate": 2.7552258480195348e-06, "loss": 0.0713, "step": 433 }, { "epoch": 1.2994011976047903, "grad_norm": 2.4031689889802923, "learning_rate": 2.734238893371667e-06, "loss": 0.072, "step": 434 }, { "epoch": 1.3023952095808382, "grad_norm": 2.7218071409818374, "learning_rate": 2.7133020528471322e-06, "loss": 0.0903, "step": 435 }, { "epoch": 1.3053892215568863, "grad_norm": 2.2768445266132833, "learning_rate": 2.6924157895271563e-06, "loss": 0.083, "step": 436 }, { "epoch": 1.3083832335329342, "grad_norm": 2.362946298931523, "learning_rate": 2.671580565374282e-06, "loss": 0.0874, "step": 437 }, { "epoch": 1.311377245508982, "grad_norm": 2.3621849094394007, "learning_rate": 2.6507968412221763e-06, "loss": 0.0726, "step": 438 }, { "epoch": 1.31437125748503, "grad_norm": 2.688107031388013, "learning_rate": 2.6300650767654234e-06, "loss": 0.0864, "step": 439 }, { "epoch": 1.3173652694610778, "grad_norm": 2.672026775085779, "learning_rate": 2.6093857305493666e-06, "loss": 0.093, "step": 440 }, { "epoch": 1.3203592814371259, "grad_norm": 2.3512163332628138, "learning_rate": 2.588759259959962e-06, "loss": 0.0829, "step": 441 }, { "epoch": 1.3233532934131738, "grad_norm": 2.4985815964333478, "learning_rate": 2.568186121213658e-06, "loss": 0.081, "step": 442 }, { "epoch": 1.3263473053892216, "grad_norm": 2.3739647733512936, "learning_rate": 2.547666769347312e-06, "loss": 0.092, "step": 443 }, { "epoch": 1.3293413173652695, "grad_norm": 2.80084747921668, "learning_rate": 2.5272016582081236e-06, "loss": 0.1023, "step": 444 }, { "epoch": 1.3323353293413174, "grad_norm": 2.4761919634327776, "learning_rate": 2.5067912404435952e-06, "loss": 0.0985, "step": 445 }, { "epoch": 1.3353293413173652, "grad_norm": 2.4396982222318533, "learning_rate": 2.486435967491516e-06, "loss": 0.0864, "step": 446 }, { "epoch": 1.3383233532934131, "grad_norm": 2.229043504996122, "learning_rate": 2.4661362895699903e-06, "loss": 0.0799, "step": 447 }, { "epoch": 1.341317365269461, "grad_norm": 2.612520951542071, "learning_rate": 2.445892655667462e-06, "loss": 0.1195, "step": 448 }, { "epoch": 1.3443113772455089, "grad_norm": 2.7201016787718477, "learning_rate": 2.425705513532798e-06, "loss": 0.1129, "step": 449 }, { "epoch": 1.347305389221557, "grad_norm": 2.464872825915462, "learning_rate": 2.4055753096653795e-06, "loss": 0.0919, "step": 450 }, { "epoch": 1.3502994011976048, "grad_norm": 2.8642629181391093, "learning_rate": 2.3855024893052286e-06, "loss": 0.095, "step": 451 }, { "epoch": 1.3532934131736527, "grad_norm": 2.6002826040762237, "learning_rate": 2.365487496423152e-06, "loss": 0.1017, "step": 452 }, { "epoch": 1.3562874251497006, "grad_norm": 2.3477494728226636, "learning_rate": 2.3455307737109338e-06, "loss": 0.08, "step": 453 }, { "epoch": 1.3592814371257484, "grad_norm": 2.502432722588937, "learning_rate": 2.3256327625715345e-06, "loss": 0.0859, "step": 454 }, { "epoch": 1.3622754491017965, "grad_norm": 2.2267576070009736, "learning_rate": 2.3057939031093346e-06, "loss": 0.0656, "step": 455 }, { "epoch": 1.3652694610778444, "grad_norm": 2.320571608645611, "learning_rate": 2.2860146341203936e-06, "loss": 0.0733, "step": 456 }, { "epoch": 1.3682634730538923, "grad_norm": 2.253652461888129, "learning_rate": 2.2662953930827546e-06, "loss": 0.1042, "step": 457 }, { "epoch": 1.3712574850299402, "grad_norm": 2.282432484813414, "learning_rate": 2.2466366161467528e-06, "loss": 0.0741, "step": 458 }, { "epoch": 1.374251497005988, "grad_norm": 2.478298677207742, "learning_rate": 2.227038738125385e-06, "loss": 0.0808, "step": 459 }, { "epoch": 1.377245508982036, "grad_norm": 2.68142376784311, "learning_rate": 2.207502192484685e-06, "loss": 0.0917, "step": 460 }, { "epoch": 1.3802395209580838, "grad_norm": 2.3237776495588838, "learning_rate": 2.188027411334131e-06, "loss": 0.076, "step": 461 }, { "epoch": 1.3832335329341316, "grad_norm": 2.426499624350088, "learning_rate": 2.1686148254171012e-06, "loss": 0.0898, "step": 462 }, { "epoch": 1.3862275449101795, "grad_norm": 2.3359584097098973, "learning_rate": 2.1492648641013305e-06, "loss": 0.0656, "step": 463 }, { "epoch": 1.3892215568862276, "grad_norm": 2.130176374730695, "learning_rate": 2.1299779553694323e-06, "loss": 0.0729, "step": 464 }, { "epoch": 1.3922155688622755, "grad_norm": 2.812073488420569, "learning_rate": 2.1107545258094135e-06, "loss": 0.0998, "step": 465 }, { "epoch": 1.3952095808383234, "grad_norm": 2.4104924344865077, "learning_rate": 2.0915950006052555e-06, "loss": 0.0686, "step": 466 }, { "epoch": 1.3982035928143712, "grad_norm": 2.2452603583052135, "learning_rate": 2.0724998035274947e-06, "loss": 0.0785, "step": 467 }, { "epoch": 1.401197604790419, "grad_norm": 1.9111238356438913, "learning_rate": 2.053469356923865e-06, "loss": 0.0618, "step": 468 }, { "epoch": 1.4041916167664672, "grad_norm": 2.1623563391061995, "learning_rate": 2.0345040817099433e-06, "loss": 0.0766, "step": 469 }, { "epoch": 1.407185628742515, "grad_norm": 1.8759045435080774, "learning_rate": 2.0156043973598475e-06, "loss": 0.0809, "step": 470 }, { "epoch": 1.410179640718563, "grad_norm": 2.8450263935312075, "learning_rate": 1.996770721896957e-06, "loss": 0.0803, "step": 471 }, { "epoch": 1.4131736526946108, "grad_norm": 2.170304023563168, "learning_rate": 1.9780034718846653e-06, "loss": 0.0602, "step": 472 }, { "epoch": 1.4161676646706587, "grad_norm": 2.5472090603705384, "learning_rate": 1.9593030624171683e-06, "loss": 0.0928, "step": 473 }, { "epoch": 1.4191616766467066, "grad_norm": 2.767302312131681, "learning_rate": 1.9406699071102774e-06, "loss": 0.0969, "step": 474 }, { "epoch": 1.4221556886227544, "grad_norm": 2.247030795908163, "learning_rate": 1.9221044180922833e-06, "loss": 0.0751, "step": 475 }, { "epoch": 1.4251497005988023, "grad_norm": 2.415714976742252, "learning_rate": 1.9036070059948253e-06, "loss": 0.0855, "step": 476 }, { "epoch": 1.4281437125748502, "grad_norm": 3.0679079414951245, "learning_rate": 1.885178079943823e-06, "loss": 0.0959, "step": 477 }, { "epoch": 1.4311377245508983, "grad_norm": 2.495840812806855, "learning_rate": 1.866818047550419e-06, "loss": 0.1148, "step": 478 }, { "epoch": 1.4341317365269461, "grad_norm": 2.19585448773456, "learning_rate": 1.8485273149019655e-06, "loss": 0.0807, "step": 479 }, { "epoch": 1.437125748502994, "grad_norm": 2.2934319271012265, "learning_rate": 1.8303062865530407e-06, "loss": 0.0667, "step": 480 }, { "epoch": 1.4401197604790419, "grad_norm": 2.3308966036506873, "learning_rate": 1.8121553655165058e-06, "loss": 0.0689, "step": 481 }, { "epoch": 1.4431137724550898, "grad_norm": 2.340176767680481, "learning_rate": 1.7940749532545832e-06, "loss": 0.0796, "step": 482 }, { "epoch": 1.4461077844311379, "grad_norm": 2.76918667713789, "learning_rate": 1.7760654496699876e-06, "loss": 0.0795, "step": 483 }, { "epoch": 1.4491017964071857, "grad_norm": 2.4276449868301015, "learning_rate": 1.7581272530970666e-06, "loss": 0.0896, "step": 484 }, { "epoch": 1.4520958083832336, "grad_norm": 2.298252678157275, "learning_rate": 1.7402607602930106e-06, "loss": 0.0748, "step": 485 }, { "epoch": 1.4550898203592815, "grad_norm": 2.34354729246804, "learning_rate": 1.7224663664290537e-06, "loss": 0.08, "step": 486 }, { "epoch": 1.4580838323353293, "grad_norm": 2.1867886653200523, "learning_rate": 1.7047444650817518e-06, "loss": 0.0921, "step": 487 }, { "epoch": 1.4610778443113772, "grad_norm": 2.2458628039680026, "learning_rate": 1.6870954482242707e-06, "loss": 0.0749, "step": 488 }, { "epoch": 1.464071856287425, "grad_norm": 2.342702105030811, "learning_rate": 1.669519706217711e-06, "loss": 0.0861, "step": 489 }, { "epoch": 1.467065868263473, "grad_norm": 2.8411677394601087, "learning_rate": 1.652017627802487e-06, "loss": 0.1015, "step": 490 }, { "epoch": 1.4700598802395208, "grad_norm": 2.4697848252295156, "learning_rate": 1.6345896000897122e-06, "loss": 0.0855, "step": 491 }, { "epoch": 1.473053892215569, "grad_norm": 2.320665355940406, "learning_rate": 1.6172360085526567e-06, "loss": 0.086, "step": 492 }, { "epoch": 1.4760479041916168, "grad_norm": 2.251662589032052, "learning_rate": 1.5999572370182016e-06, "loss": 0.0984, "step": 493 }, { "epoch": 1.4790419161676647, "grad_norm": 2.6032190126524335, "learning_rate": 1.5827536676583643e-06, "loss": 0.084, "step": 494 }, { "epoch": 1.4820359281437125, "grad_norm": 3.0994775643678802, "learning_rate": 1.5656256809818343e-06, "loss": 0.0998, "step": 495 }, { "epoch": 1.4850299401197604, "grad_norm": 2.3467327121176385, "learning_rate": 1.54857365582557e-06, "loss": 0.076, "step": 496 }, { "epoch": 1.4880239520958085, "grad_norm": 2.6583179315918306, "learning_rate": 1.5315979693464039e-06, "loss": 0.0868, "step": 497 }, { "epoch": 1.4910179640718564, "grad_norm": 2.440330197125349, "learning_rate": 1.5146989970127158e-06, "loss": 0.0727, "step": 498 }, { "epoch": 1.4940119760479043, "grad_norm": 2.9771490718263034, "learning_rate": 1.4978771125961177e-06, "loss": 0.1121, "step": 499 }, { "epoch": 1.4970059880239521, "grad_norm": 2.1880519741861124, "learning_rate": 1.4811326881631937e-06, "loss": 0.0806, "step": 500 }, { "epoch": 1.5, "grad_norm": 2.90412973520403, "learning_rate": 1.4644660940672628e-06, "loss": 0.0866, "step": 501 }, { "epoch": 1.5029940119760479, "grad_norm": 2.8519720464968117, "learning_rate": 1.4478776989401949e-06, "loss": 0.0949, "step": 502 }, { "epoch": 1.5059880239520957, "grad_norm": 2.5210572379918896, "learning_rate": 1.4313678696842559e-06, "loss": 0.0924, "step": 503 }, { "epoch": 1.5089820359281436, "grad_norm": 2.2828189215276797, "learning_rate": 1.4149369714639856e-06, "loss": 0.0759, "step": 504 }, { "epoch": 1.5119760479041915, "grad_norm": 2.7041539377821118, "learning_rate": 1.3985853676981316e-06, "loss": 0.0845, "step": 505 }, { "epoch": 1.5149700598802394, "grad_norm": 2.412095515053398, "learning_rate": 1.3823134200516043e-06, "loss": 0.0666, "step": 506 }, { "epoch": 1.5179640718562875, "grad_norm": 2.23437972137475, "learning_rate": 1.366121488427481e-06, "loss": 0.0687, "step": 507 }, { "epoch": 1.5209580838323353, "grad_norm": 2.1315482461838746, "learning_rate": 1.3500099309590397e-06, "loss": 0.0736, "step": 508 }, { "epoch": 1.5239520958083832, "grad_norm": 2.7643385442998527, "learning_rate": 1.3339791040018479e-06, "loss": 0.0731, "step": 509 }, { "epoch": 1.5269461077844313, "grad_norm": 2.393313713353166, "learning_rate": 1.3180293621258694e-06, "loss": 0.095, "step": 510 }, { "epoch": 1.5299401197604792, "grad_norm": 2.5917132096798943, "learning_rate": 1.3021610581076316e-06, "loss": 0.0809, "step": 511 }, { "epoch": 1.532934131736527, "grad_norm": 2.5719111448733107, "learning_rate": 1.2863745429224145e-06, "loss": 0.0696, "step": 512 }, { "epoch": 1.535928143712575, "grad_norm": 2.27033878092526, "learning_rate": 1.270670165736499e-06, "loss": 0.0713, "step": 513 }, { "epoch": 1.5389221556886228, "grad_norm": 2.5647133643006055, "learning_rate": 1.2550482738994284e-06, "loss": 0.1017, "step": 514 }, { "epoch": 1.5419161676646707, "grad_norm": 2.629741411644176, "learning_rate": 1.239509212936343e-06, "loss": 0.1036, "step": 515 }, { "epoch": 1.5449101796407185, "grad_norm": 2.464616826184895, "learning_rate": 1.22405332654032e-06, "loss": 0.081, "step": 516 }, { "epoch": 1.5479041916167664, "grad_norm": 2.3087742343886175, "learning_rate": 1.2086809565647877e-06, "loss": 0.1093, "step": 517 }, { "epoch": 1.5508982035928143, "grad_norm": 2.3815092488939777, "learning_rate": 1.1933924430159571e-06, "loss": 0.0705, "step": 518 }, { "epoch": 1.5538922155688621, "grad_norm": 2.2578201872874737, "learning_rate": 1.1781881240452958e-06, "loss": 0.0814, "step": 519 }, { "epoch": 1.55688622754491, "grad_norm": 2.6855390978178777, "learning_rate": 1.1630683359420653e-06, "loss": 0.0956, "step": 520 }, { "epoch": 1.5598802395209581, "grad_norm": 2.0997830377544573, "learning_rate": 1.1480334131258626e-06, "loss": 0.0678, "step": 521 }, { "epoch": 1.562874251497006, "grad_norm": 2.636827244660342, "learning_rate": 1.1330836881392405e-06, "loss": 0.0869, "step": 522 }, { "epoch": 1.5658682634730539, "grad_norm": 2.1910000224384576, "learning_rate": 1.11821949164034e-06, "loss": 0.0695, "step": 523 }, { "epoch": 1.568862275449102, "grad_norm": 2.1438669856035175, "learning_rate": 1.103441152395588e-06, "loss": 0.0746, "step": 524 }, { "epoch": 1.5718562874251498, "grad_norm": 2.4410338094391406, "learning_rate": 1.088748997272414e-06, "loss": 0.086, "step": 525 }, { "epoch": 1.5748502994011977, "grad_norm": 2.363059374902875, "learning_rate": 1.0741433512320316e-06, "loss": 0.0693, "step": 526 }, { "epoch": 1.5778443113772456, "grad_norm": 2.785134779280438, "learning_rate": 1.0596245373222424e-06, "loss": 0.0772, "step": 527 }, { "epoch": 1.5808383233532934, "grad_norm": 2.6633628369879947, "learning_rate": 1.045192876670298e-06, "loss": 0.0826, "step": 528 }, { "epoch": 1.5838323353293413, "grad_norm": 2.620101453431677, "learning_rate": 1.0308486884757868e-06, "loss": 0.111, "step": 529 }, { "epoch": 1.5868263473053892, "grad_norm": 2.3016926267636584, "learning_rate": 1.0165922900035886e-06, "loss": 0.0777, "step": 530 }, { "epoch": 1.589820359281437, "grad_norm": 2.0143355130466656, "learning_rate": 1.0024239965768417e-06, "loss": 0.066, "step": 531 }, { "epoch": 1.592814371257485, "grad_norm": 2.1546426602285353, "learning_rate": 9.883441215699824e-07, "loss": 0.0581, "step": 532 }, { "epoch": 1.5958083832335328, "grad_norm": 2.8197859054823335, "learning_rate": 9.74352976401805e-07, "loss": 0.0937, "step": 533 }, { "epoch": 1.5988023952095807, "grad_norm": 3.325968612952348, "learning_rate": 9.604508705285765e-07, "loss": 0.0973, "step": 534 }, { "epoch": 1.6017964071856288, "grad_norm": 2.300476773192775, "learning_rate": 9.466381114371942e-07, "loss": 0.0944, "step": 535 }, { "epoch": 1.6047904191616766, "grad_norm": 2.4520541745135054, "learning_rate": 9.329150046383773e-07, "loss": 0.082, "step": 536 }, { "epoch": 1.6077844311377245, "grad_norm": 2.405818801784024, "learning_rate": 9.192818536599213e-07, "loss": 0.0888, "step": 537 }, { "epoch": 1.6107784431137726, "grad_norm": 2.6508764730051046, "learning_rate": 9.057389600399719e-07, "loss": 0.095, "step": 538 }, { "epoch": 1.6137724550898205, "grad_norm": 2.508705081809098, "learning_rate": 8.922866233203681e-07, "loss": 0.1114, "step": 539 }, { "epoch": 1.6167664670658684, "grad_norm": 2.117775009252432, "learning_rate": 8.789251410400024e-07, "loss": 0.0684, "step": 540 }, { "epoch": 1.6197604790419162, "grad_norm": 2.0008899092510872, "learning_rate": 8.65654808728259e-07, "loss": 0.0994, "step": 541 }, { "epoch": 1.622754491017964, "grad_norm": 2.5850732525556026, "learning_rate": 8.524759198984567e-07, "loss": 0.0706, "step": 542 }, { "epoch": 1.625748502994012, "grad_norm": 2.543045349760796, "learning_rate": 8.393887660413719e-07, "loss": 0.0969, "step": 543 }, { "epoch": 1.6287425149700598, "grad_norm": 2.803919150017087, "learning_rate": 8.263936366187825e-07, "loss": 0.1151, "step": 544 }, { "epoch": 1.6317365269461077, "grad_norm": 2.2668640511683975, "learning_rate": 8.134908190570723e-07, "loss": 0.0923, "step": 545 }, { "epoch": 1.6347305389221556, "grad_norm": 2.6394489626089928, "learning_rate": 8.006805987408705e-07, "loss": 0.0854, "step": 546 }, { "epoch": 1.6377245508982035, "grad_norm": 2.219130494954283, "learning_rate": 7.879632590067354e-07, "loss": 0.084, "step": 547 }, { "epoch": 1.6407185628742516, "grad_norm": 2.1693447437368896, "learning_rate": 7.753390811368972e-07, "loss": 0.0783, "step": 548 }, { "epoch": 1.6437125748502994, "grad_norm": 2.5481924422943485, "learning_rate": 7.628083443530287e-07, "loss": 0.0844, "step": 549 }, { "epoch": 1.6467065868263473, "grad_norm": 2.6844665329630373, "learning_rate": 7.503713258100726e-07, "loss": 0.0893, "step": 550 }, { "epoch": 1.6497005988023952, "grad_norm": 2.5194659576502936, "learning_rate": 7.380283005901084e-07, "loss": 0.1014, "step": 551 }, { "epoch": 1.6526946107784433, "grad_norm": 2.1646068735670996, "learning_rate": 7.257795416962754e-07, "loss": 0.068, "step": 552 }, { "epoch": 1.6556886227544911, "grad_norm": 1.9543904709466815, "learning_rate": 7.136253200467231e-07, "loss": 0.0539, "step": 553 }, { "epoch": 1.658682634730539, "grad_norm": 2.1321399035807826, "learning_rate": 7.015659044686307e-07, "loss": 0.073, "step": 554 }, { "epoch": 1.6616766467065869, "grad_norm": 2.3568775857325526, "learning_rate": 6.896015616922535e-07, "loss": 0.0736, "step": 555 }, { "epoch": 1.6646706586826348, "grad_norm": 2.5426882404016102, "learning_rate": 6.777325563450282e-07, "loss": 0.0974, "step": 556 }, { "epoch": 1.6676646706586826, "grad_norm": 2.469589157601292, "learning_rate": 6.659591509457125e-07, "loss": 0.1087, "step": 557 }, { "epoch": 1.6706586826347305, "grad_norm": 2.2823894535206666, "learning_rate": 6.542816058985896e-07, "loss": 0.0714, "step": 558 }, { "epoch": 1.6736526946107784, "grad_norm": 2.470058777281258, "learning_rate": 6.427001794876974e-07, "loss": 0.0895, "step": 559 }, { "epoch": 1.6766467065868262, "grad_norm": 2.0942154797002823, "learning_rate": 6.312151278711237e-07, "loss": 0.0612, "step": 560 }, { "epoch": 1.6796407185628741, "grad_norm": 2.0714597252460067, "learning_rate": 6.198267050753387e-07, "loss": 0.0737, "step": 561 }, { "epoch": 1.6826347305389222, "grad_norm": 2.2366872980522263, "learning_rate": 6.085351629895736e-07, "loss": 0.0796, "step": 562 }, { "epoch": 1.68562874251497, "grad_norm": 2.3919855014615283, "learning_rate": 5.973407513602514e-07, "loss": 0.0665, "step": 563 }, { "epoch": 1.688622754491018, "grad_norm": 2.548960499394686, "learning_rate": 5.862437177854629e-07, "loss": 0.101, "step": 564 }, { "epoch": 1.6916167664670658, "grad_norm": 2.401571398603268, "learning_rate": 5.752443077094927e-07, "loss": 0.0682, "step": 565 }, { "epoch": 1.694610778443114, "grad_norm": 2.533419276502617, "learning_rate": 5.643427644173838e-07, "loss": 0.0952, "step": 566 }, { "epoch": 1.6976047904191618, "grad_norm": 2.2886049272773943, "learning_rate": 5.535393290295643e-07, "loss": 0.0884, "step": 567 }, { "epoch": 1.7005988023952097, "grad_norm": 2.2061808783229666, "learning_rate": 5.428342404965076e-07, "loss": 0.0793, "step": 568 }, { "epoch": 1.7035928143712575, "grad_norm": 2.4037840567808777, "learning_rate": 5.322277355934557e-07, "loss": 0.0878, "step": 569 }, { "epoch": 1.7065868263473054, "grad_norm": 2.1200676472731157, "learning_rate": 5.217200489151714e-07, "loss": 0.0641, "step": 570 }, { "epoch": 1.7095808383233533, "grad_norm": 2.163742241466742, "learning_rate": 5.113114128707592e-07, "loss": 0.077, "step": 571 }, { "epoch": 1.7125748502994012, "grad_norm": 2.371432640667848, "learning_rate": 5.010020576785174e-07, "loss": 0.0863, "step": 572 }, { "epoch": 1.715568862275449, "grad_norm": 2.3615318699713934, "learning_rate": 4.907922113608532e-07, "loss": 0.0702, "step": 573 }, { "epoch": 1.718562874251497, "grad_norm": 2.5093568937664057, "learning_rate": 4.806820997392325e-07, "loss": 0.1087, "step": 574 }, { "epoch": 1.7215568862275448, "grad_norm": 2.0260915874610497, "learning_rate": 4.7067194642919036e-07, "loss": 0.0639, "step": 575 }, { "epoch": 1.7245508982035929, "grad_norm": 2.638565553393085, "learning_rate": 4.607619728353818e-07, "loss": 0.0833, "step": 576 }, { "epoch": 1.7275449101796407, "grad_norm": 2.677538233224939, "learning_rate": 4.50952398146689e-07, "loss": 0.0899, "step": 577 }, { "epoch": 1.7305389221556886, "grad_norm": 2.238442089200804, "learning_rate": 4.4124343933136525e-07, "loss": 0.064, "step": 578 }, { "epoch": 1.7335329341317365, "grad_norm": 2.310152836148933, "learning_rate": 4.3163531113224466e-07, "loss": 0.094, "step": 579 }, { "epoch": 1.7365269461077846, "grad_norm": 2.7474234093746523, "learning_rate": 4.221282260619891e-07, "loss": 0.0979, "step": 580 }, { "epoch": 1.7395209580838324, "grad_norm": 1.9309624313576552, "learning_rate": 4.127223943983849e-07, "loss": 0.0638, "step": 581 }, { "epoch": 1.7425149700598803, "grad_norm": 2.454567305476243, "learning_rate": 4.03418024179697e-07, "loss": 0.0736, "step": 582 }, { "epoch": 1.7455089820359282, "grad_norm": 2.218884614733349, "learning_rate": 3.9421532120006544e-07, "loss": 0.0967, "step": 583 }, { "epoch": 1.748502994011976, "grad_norm": 2.023858188170693, "learning_rate": 3.851144890049535e-07, "loss": 0.0801, "step": 584 }, { "epoch": 1.751497005988024, "grad_norm": 2.375449954577522, "learning_rate": 3.761157288866418e-07, "loss": 0.0933, "step": 585 }, { "epoch": 1.7544910179640718, "grad_norm": 2.170076696643232, "learning_rate": 3.672192398797858e-07, "loss": 0.1001, "step": 586 }, { "epoch": 1.7574850299401197, "grad_norm": 2.785145421650509, "learning_rate": 3.58425218757002e-07, "loss": 0.0975, "step": 587 }, { "epoch": 1.7604790419161676, "grad_norm": 2.4974199829043533, "learning_rate": 3.497338600245254e-07, "loss": 0.0724, "step": 588 }, { "epoch": 1.7634730538922154, "grad_norm": 2.287619934381915, "learning_rate": 3.4114535591790233e-07, "loss": 0.0745, "step": 589 }, { "epoch": 1.7664670658682635, "grad_norm": 2.6875118277177354, "learning_rate": 3.326598963977395e-07, "loss": 0.0801, "step": 590 }, { "epoch": 1.7694610778443114, "grad_norm": 2.5089743164866904, "learning_rate": 3.242776691455013e-07, "loss": 0.0868, "step": 591 }, { "epoch": 1.7724550898203593, "grad_norm": 2.227707269716856, "learning_rate": 3.159988595593616e-07, "loss": 0.0768, "step": 592 }, { "epoch": 1.7754491017964071, "grad_norm": 2.1354056262337253, "learning_rate": 3.078236507501015e-07, "loss": 0.0695, "step": 593 }, { "epoch": 1.7784431137724552, "grad_norm": 2.3238018231153488, "learning_rate": 2.9975222353705757e-07, "loss": 0.0862, "step": 594 }, { "epoch": 1.781437125748503, "grad_norm": 2.358788881327816, "learning_rate": 2.917847564441256e-07, "loss": 0.0891, "step": 595 }, { "epoch": 1.784431137724551, "grad_norm": 2.2217421971868117, "learning_rate": 2.839214256958106e-07, "loss": 0.092, "step": 596 }, { "epoch": 1.7874251497005988, "grad_norm": 2.3153899338119777, "learning_rate": 2.7616240521332884e-07, "loss": 0.0778, "step": 597 }, { "epoch": 1.7904191616766467, "grad_norm": 2.7527356692765466, "learning_rate": 2.6850786661076047e-07, "loss": 0.0883, "step": 598 }, { "epoch": 1.7934131736526946, "grad_norm": 2.1272072945487754, "learning_rate": 2.6095797919125533e-07, "loss": 0.0677, "step": 599 }, { "epoch": 1.7964071856287425, "grad_norm": 2.1558764316712367, "learning_rate": 2.5351290994328703e-07, "loss": 0.0795, "step": 600 }, { "epoch": 1.7964071856287425, "eval_loss": 0.19479966163635254, "eval_runtime": 1.6022, "eval_samples_per_second": 33.703, "eval_steps_per_second": 8.738, "step": 600 }, { "epoch": 1.7994011976047903, "grad_norm": 2.2514975675072955, "learning_rate": 2.4617282353696093e-07, "loss": 0.0714, "step": 601 }, { "epoch": 1.8023952095808382, "grad_norm": 2.695664954401551, "learning_rate": 2.3893788232036807e-07, "loss": 0.1076, "step": 602 }, { "epoch": 1.805389221556886, "grad_norm": 2.5229853920864613, "learning_rate": 2.318082463160032e-07, "loss": 0.1023, "step": 603 }, { "epoch": 1.8083832335329342, "grad_norm": 2.237906256902017, "learning_rate": 2.2478407321721295e-07, "loss": 0.0863, "step": 604 }, { "epoch": 1.811377245508982, "grad_norm": 2.391742333906458, "learning_rate": 2.1786551838471892e-07, "loss": 0.1001, "step": 605 }, { "epoch": 1.81437125748503, "grad_norm": 2.3902870551838022, "learning_rate": 2.1105273484317402e-07, "loss": 0.0662, "step": 606 }, { "epoch": 1.8173652694610778, "grad_norm": 2.0461128077774933, "learning_rate": 2.043458732777831e-07, "loss": 0.0746, "step": 607 }, { "epoch": 1.8203592814371259, "grad_norm": 2.9151088126673077, "learning_rate": 1.9774508203096843e-07, "loss": 0.0828, "step": 608 }, { "epoch": 1.8233532934131738, "grad_norm": 2.1654371297378634, "learning_rate": 1.9125050709908388e-07, "loss": 0.0752, "step": 609 }, { "epoch": 1.8263473053892216, "grad_norm": 2.174480809884344, "learning_rate": 1.8486229212919482e-07, "loss": 0.0775, "step": 610 }, { "epoch": 1.8293413173652695, "grad_norm": 2.111881449102193, "learning_rate": 1.7858057841589281e-07, "loss": 0.0661, "step": 611 }, { "epoch": 1.8323353293413174, "grad_norm": 2.1263859064761124, "learning_rate": 1.7240550489817652e-07, "loss": 0.0774, "step": 612 }, { "epoch": 1.8353293413173652, "grad_norm": 2.738357240475425, "learning_rate": 1.66337208156373e-07, "loss": 0.0908, "step": 613 }, { "epoch": 1.8383233532934131, "grad_norm": 2.889858013777749, "learning_rate": 1.6037582240912175e-07, "loss": 0.1113, "step": 614 }, { "epoch": 1.841317365269461, "grad_norm": 2.650366897515821, "learning_rate": 1.5452147951040165e-07, "loss": 0.0941, "step": 615 }, { "epoch": 1.8443113772455089, "grad_norm": 2.6412791778242353, "learning_rate": 1.4877430894662037e-07, "loss": 0.1004, "step": 616 }, { "epoch": 1.8473053892215567, "grad_norm": 2.2833276813178474, "learning_rate": 1.4313443783374405e-07, "loss": 0.0757, "step": 617 }, { "epoch": 1.8502994011976048, "grad_norm": 2.118265978253269, "learning_rate": 1.3760199091449045e-07, "loss": 0.078, "step": 618 }, { "epoch": 1.8532934131736527, "grad_norm": 2.2924512302557694, "learning_rate": 1.3217709055556638e-07, "loss": 0.0797, "step": 619 }, { "epoch": 1.8562874251497006, "grad_norm": 2.4905919247964867, "learning_rate": 1.268598567449647e-07, "loss": 0.0862, "step": 620 }, { "epoch": 1.8592814371257484, "grad_norm": 2.429474585872469, "learning_rate": 1.2165040708930763e-07, "loss": 0.0883, "step": 621 }, { "epoch": 1.8622754491017965, "grad_norm": 1.8655486805247627, "learning_rate": 1.1654885681124661e-07, "loss": 0.0791, "step": 622 }, { "epoch": 1.8652694610778444, "grad_norm": 2.4735509638830906, "learning_rate": 1.1155531874691372e-07, "loss": 0.0828, "step": 623 }, { "epoch": 1.8682634730538923, "grad_norm": 2.124706424588511, "learning_rate": 1.0666990334342708e-07, "loss": 0.0693, "step": 624 }, { "epoch": 1.8712574850299402, "grad_norm": 2.4308549906086228, "learning_rate": 1.0189271865644445e-07, "loss": 0.0801, "step": 625 }, { "epoch": 1.874251497005988, "grad_norm": 3.3025070792761326, "learning_rate": 9.722387034777847e-08, "loss": 0.0879, "step": 626 }, { "epoch": 1.877245508982036, "grad_norm": 2.5295650102498617, "learning_rate": 9.266346168305518e-08, "loss": 0.1074, "step": 627 }, { "epoch": 1.8802395209580838, "grad_norm": 2.246114898866838, "learning_rate": 8.821159352943142e-08, "loss": 0.0747, "step": 628 }, { "epoch": 1.8832335329341316, "grad_norm": 2.2576167348458416, "learning_rate": 8.38683643533661e-08, "loss": 0.0671, "step": 629 }, { "epoch": 1.8862275449101795, "grad_norm": 2.190919955833265, "learning_rate": 7.963387021843683e-08, "loss": 0.0596, "step": 630 }, { "epoch": 1.8892215568862274, "grad_norm": 2.546333503839789, "learning_rate": 7.550820478322285e-08, "loss": 0.1035, "step": 631 }, { "epoch": 1.8922155688622755, "grad_norm": 2.317477429694358, "learning_rate": 7.149145929922607e-08, "loss": 0.0993, "step": 632 }, { "epoch": 1.8952095808383234, "grad_norm": 2.508300763894733, "learning_rate": 6.758372260885714e-08, "loss": 0.0936, "step": 633 }, { "epoch": 1.8982035928143712, "grad_norm": 2.8703370653369107, "learning_rate": 6.378508114346982e-08, "loss": 0.109, "step": 634 }, { "epoch": 1.9011976047904193, "grad_norm": 2.320600786094049, "learning_rate": 6.009561892144744e-08, "loss": 0.0701, "step": 635 }, { "epoch": 1.9041916167664672, "grad_norm": 2.3770791584079154, "learning_rate": 5.651541754634726e-08, "loss": 0.0663, "step": 636 }, { "epoch": 1.907185628742515, "grad_norm": 2.597437140819775, "learning_rate": 5.304455620509297e-08, "loss": 0.0987, "step": 637 }, { "epoch": 1.910179640718563, "grad_norm": 2.0178692080812057, "learning_rate": 4.968311166622553e-08, "loss": 0.0592, "step": 638 }, { "epoch": 1.9131736526946108, "grad_norm": 2.219460600697386, "learning_rate": 4.643115827820399e-08, "loss": 0.0749, "step": 639 }, { "epoch": 1.9161676646706587, "grad_norm": 2.367179096804463, "learning_rate": 4.328876796776071e-08, "loss": 0.0786, "step": 640 }, { "epoch": 1.9191616766467066, "grad_norm": 2.3956393877257636, "learning_rate": 4.0256010238310936e-08, "loss": 0.0856, "step": 641 }, { "epoch": 1.9221556886227544, "grad_norm": 2.528522244782668, "learning_rate": 3.733295216841626e-08, "loss": 0.0895, "step": 642 }, { "epoch": 1.9251497005988023, "grad_norm": 3.2149498325162877, "learning_rate": 3.451965841029914e-08, "loss": 0.0849, "step": 643 }, { "epoch": 1.9281437125748502, "grad_norm": 2.1526412670142836, "learning_rate": 3.181619118841517e-08, "loss": 0.0777, "step": 644 }, { "epoch": 1.931137724550898, "grad_norm": 2.3086186163281286, "learning_rate": 2.9222610298074717e-08, "loss": 0.0603, "step": 645 }, { "epoch": 1.9341317365269461, "grad_norm": 2.12337262038326, "learning_rate": 2.673897310412288e-08, "loss": 0.0893, "step": 646 }, { "epoch": 1.937125748502994, "grad_norm": 2.1235855520591795, "learning_rate": 2.4365334539667717e-08, "loss": 0.0682, "step": 647 }, { "epoch": 1.9401197604790419, "grad_norm": 2.85628593125201, "learning_rate": 2.210174710486679e-08, "loss": 0.0818, "step": 648 }, { "epoch": 1.94311377245509, "grad_norm": 2.20598078970333, "learning_rate": 1.99482608657664e-08, "loss": 0.0726, "step": 649 }, { "epoch": 1.9461077844311379, "grad_norm": 2.1612849414531667, "learning_rate": 1.7904923453193056e-08, "loss": 0.0718, "step": 650 }, { "epoch": 1.9491017964071857, "grad_norm": 2.4904562787080984, "learning_rate": 1.5971780061701524e-08, "loss": 0.0765, "step": 651 }, { "epoch": 1.9520958083832336, "grad_norm": 2.148259961558057, "learning_rate": 1.4148873448573408e-08, "loss": 0.0628, "step": 652 }, { "epoch": 1.9550898203592815, "grad_norm": 2.3505341238717263, "learning_rate": 1.2436243932872349e-08, "loss": 0.1073, "step": 653 }, { "epoch": 1.9580838323353293, "grad_norm": 2.29141387290338, "learning_rate": 1.0833929394552523e-08, "loss": 0.0816, "step": 654 }, { "epoch": 1.9610778443113772, "grad_norm": 2.1471152345097786, "learning_rate": 9.341965273621522e-09, "loss": 0.0731, "step": 655 }, { "epoch": 1.964071856287425, "grad_norm": 2.660880892452436, "learning_rate": 7.96038456935322e-09, "loss": 0.0898, "step": 656 }, { "epoch": 1.967065868263473, "grad_norm": 2.739747158796103, "learning_rate": 6.6892178395611125e-09, "loss": 0.0884, "step": 657 }, { "epoch": 1.9700598802395208, "grad_norm": 2.4275725197627467, "learning_rate": 5.528493199922769e-09, "loss": 0.0798, "step": 658 }, { "epoch": 1.9730538922155687, "grad_norm": 2.1482789285920956, "learning_rate": 4.478236323355312e-09, "loss": 0.0738, "step": 659 }, { "epoch": 1.9760479041916168, "grad_norm": 2.5174700870260485, "learning_rate": 3.538470439448105e-09, "loss": 0.0955, "step": 660 }, { "epoch": 1.9790419161676647, "grad_norm": 2.5407259981272543, "learning_rate": 2.709216333952602e-09, "loss": 0.1027, "step": 661 }, { "epoch": 1.9820359281437125, "grad_norm": 2.2552267666167234, "learning_rate": 1.9904923483171632e-09, "loss": 0.0839, "step": 662 }, { "epoch": 1.9850299401197606, "grad_norm": 2.720144952583477, "learning_rate": 1.3823143792851545e-09, "loss": 0.0954, "step": 663 }, { "epoch": 1.9880239520958085, "grad_norm": 2.927356209157129, "learning_rate": 8.846958785418969e-10, "loss": 0.0968, "step": 664 }, { "epoch": 1.9910179640718564, "grad_norm": 2.189411638365064, "learning_rate": 4.97647852417682e-10, "loss": 0.0796, "step": 665 }, { "epoch": 1.9940119760479043, "grad_norm": 2.0020935532239195, "learning_rate": 2.2117886164407797e-10, "loss": 0.068, "step": 666 }, { "epoch": 1.9970059880239521, "grad_norm": 2.1632371595702566, "learning_rate": 5.529502116519148e-11, "loss": 0.0928, "step": 667 }, { "epoch": 2.0, "grad_norm": 1.675598514997588, "learning_rate": 0.0, "loss": 0.0435, "step": 668 }, { "epoch": 2.0, "step": 668, "total_flos": 3605863612416.0, "train_loss": 0.12988467803392226, "train_runtime": 403.4892, "train_samples_per_second": 26.415, "train_steps_per_second": 1.656 } ], "logging_steps": 1, "max_steps": 668, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 2000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3605863612416.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }