{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 412, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0048543689320388345, "grad_norm": 3.3324859196579646, "learning_rate": 9.999854640567861e-06, "loss": 0.1339, "step": 1 }, { "epoch": 0.009708737864077669, "grad_norm": 3.8088042361483816, "learning_rate": 9.999418570723189e-06, "loss": 0.1354, "step": 2 }, { "epoch": 0.014563106796116505, "grad_norm": 5.274233478446681, "learning_rate": 9.998691815820732e-06, "loss": 0.2009, "step": 3 }, { "epoch": 0.019417475728155338, "grad_norm": 4.101699811840383, "learning_rate": 9.997674418116759e-06, "loss": 0.1982, "step": 4 }, { "epoch": 0.024271844660194174, "grad_norm": 3.924795885151193, "learning_rate": 9.996366436766612e-06, "loss": 0.1883, "step": 5 }, { "epoch": 0.02912621359223301, "grad_norm": 5.771957604254228, "learning_rate": 9.994767947821261e-06, "loss": 0.188, "step": 6 }, { "epoch": 0.03398058252427184, "grad_norm": 4.039324853603417, "learning_rate": 9.992879044222887e-06, "loss": 0.1602, "step": 7 }, { "epoch": 0.038834951456310676, "grad_norm": 3.450341344849428, "learning_rate": 9.99069983579947e-06, "loss": 0.1716, "step": 8 }, { "epoch": 0.043689320388349516, "grad_norm": 3.7152133363818325, "learning_rate": 9.988230449258409e-06, "loss": 0.1584, "step": 9 }, { "epoch": 0.04854368932038835, "grad_norm": 2.9403672361375413, "learning_rate": 9.985471028179155e-06, "loss": 0.1338, "step": 10 }, { "epoch": 0.05339805825242718, "grad_norm": 3.6346123927161558, "learning_rate": 9.982421733004857e-06, "loss": 0.1413, "step": 11 }, { "epoch": 0.05825242718446602, "grad_norm": 3.918759862991223, "learning_rate": 9.979082741033047e-06, "loss": 0.1571, "step": 12 }, { "epoch": 0.06310679611650485, "grad_norm": 3.3243324871274846, "learning_rate": 9.975454246405312e-06, "loss": 0.1373, "step": 13 }, { "epoch": 0.06796116504854369, "grad_norm": 4.090995406850703, "learning_rate": 9.971536460096021e-06, "loss": 0.2064, "step": 14 }, { "epoch": 0.07281553398058252, "grad_norm": 4.5651807246739535, "learning_rate": 9.96732960990005e-06, "loss": 0.213, "step": 15 }, { "epoch": 0.07766990291262135, "grad_norm": 3.8522165104605186, "learning_rate": 9.96283394041954e-06, "loss": 0.1806, "step": 16 }, { "epoch": 0.0825242718446602, "grad_norm": 4.090915249944868, "learning_rate": 9.95804971304968e-06, "loss": 0.1594, "step": 17 }, { "epoch": 0.08737864077669903, "grad_norm": 3.343034439706098, "learning_rate": 9.952977205963496e-06, "loss": 0.143, "step": 18 }, { "epoch": 0.09223300970873786, "grad_norm": 3.2771634678459036, "learning_rate": 9.94761671409569e-06, "loss": 0.1604, "step": 19 }, { "epoch": 0.0970873786407767, "grad_norm": 3.4631851530033657, "learning_rate": 9.941968549125481e-06, "loss": 0.1618, "step": 20 }, { "epoch": 0.10194174757281553, "grad_norm": 3.928255474637941, "learning_rate": 9.936033039458494e-06, "loss": 0.1778, "step": 21 }, { "epoch": 0.10679611650485436, "grad_norm": 3.3479570283155202, "learning_rate": 9.929810530207651e-06, "loss": 0.1591, "step": 22 }, { "epoch": 0.11165048543689321, "grad_norm": 3.6975883529242646, "learning_rate": 9.923301383173119e-06, "loss": 0.2006, "step": 23 }, { "epoch": 0.11650485436893204, "grad_norm": 3.469665362839314, "learning_rate": 9.916505976821262e-06, "loss": 0.1657, "step": 24 }, { "epoch": 0.12135922330097088, "grad_norm": 3.3643581564878673, "learning_rate": 9.909424706262647e-06, "loss": 0.1569, "step": 25 }, { "epoch": 0.1262135922330097, "grad_norm": 4.110694436156542, "learning_rate": 9.902057983229059e-06, "loss": 0.1909, "step": 26 }, { "epoch": 0.13106796116504854, "grad_norm": 3.186323923132206, "learning_rate": 9.894406236049569e-06, "loss": 0.163, "step": 27 }, { "epoch": 0.13592233009708737, "grad_norm": 3.5498332735613127, "learning_rate": 9.886469909625624e-06, "loss": 0.196, "step": 28 }, { "epoch": 0.1407766990291262, "grad_norm": 3.9980031295006313, "learning_rate": 9.87824946540519e-06, "loss": 0.208, "step": 29 }, { "epoch": 0.14563106796116504, "grad_norm": 3.4906745199009417, "learning_rate": 9.869745381355906e-06, "loss": 0.1664, "step": 30 }, { "epoch": 0.15048543689320387, "grad_norm": 3.954794586878399, "learning_rate": 9.860958151937303e-06, "loss": 0.1877, "step": 31 }, { "epoch": 0.1553398058252427, "grad_norm": 3.6372789508629273, "learning_rate": 9.851888288072053e-06, "loss": 0.1735, "step": 32 }, { "epoch": 0.16019417475728157, "grad_norm": 3.9820299514191384, "learning_rate": 9.842536317116262e-06, "loss": 0.2067, "step": 33 }, { "epoch": 0.1650485436893204, "grad_norm": 3.7102209529281174, "learning_rate": 9.832902782828801e-06, "loss": 0.1915, "step": 34 }, { "epoch": 0.16990291262135923, "grad_norm": 3.925675916083603, "learning_rate": 9.822988245339701e-06, "loss": 0.1979, "step": 35 }, { "epoch": 0.17475728155339806, "grad_norm": 3.918214682037897, "learning_rate": 9.81279328111758e-06, "loss": 0.1596, "step": 36 }, { "epoch": 0.1796116504854369, "grad_norm": 9.706515279117301, "learning_rate": 9.802318482936121e-06, "loss": 2.2571, "step": 37 }, { "epoch": 0.18446601941747573, "grad_norm": 6.621327724804455, "learning_rate": 9.791564459839609e-06, "loss": 1.938, "step": 38 }, { "epoch": 0.18932038834951456, "grad_norm": 3.7869250833437826, "learning_rate": 9.780531837107519e-06, "loss": 0.2153, "step": 39 }, { "epoch": 0.1941747572815534, "grad_norm": 4.474156895071826, "learning_rate": 9.769221256218165e-06, "loss": 0.2017, "step": 40 }, { "epoch": 0.19902912621359223, "grad_norm": 4.084460872286135, "learning_rate": 9.75763337481139e-06, "loss": 0.2182, "step": 41 }, { "epoch": 0.20388349514563106, "grad_norm": 3.870693933215402, "learning_rate": 9.745768866650339e-06, "loss": 0.2244, "step": 42 }, { "epoch": 0.2087378640776699, "grad_norm": 2.902378281214243, "learning_rate": 9.73362842158228e-06, "loss": 0.1467, "step": 43 }, { "epoch": 0.21359223300970873, "grad_norm": 3.248116446046984, "learning_rate": 9.721212745498493e-06, "loss": 0.1843, "step": 44 }, { "epoch": 0.21844660194174756, "grad_norm": 3.667256599988585, "learning_rate": 9.70852256029323e-06, "loss": 0.1765, "step": 45 }, { "epoch": 0.22330097087378642, "grad_norm": 3.839808524241103, "learning_rate": 9.695558603821735e-06, "loss": 0.2249, "step": 46 }, { "epoch": 0.22815533980582525, "grad_norm": 3.561913372270993, "learning_rate": 9.682321629857348e-06, "loss": 0.1945, "step": 47 }, { "epoch": 0.23300970873786409, "grad_norm": 3.7140607428554686, "learning_rate": 9.66881240804768e-06, "loss": 0.1923, "step": 48 }, { "epoch": 0.23786407766990292, "grad_norm": 4.162473919082487, "learning_rate": 9.655031723869848e-06, "loss": 0.2106, "step": 49 }, { "epoch": 0.24271844660194175, "grad_norm": 4.088833429529486, "learning_rate": 9.64098037858483e-06, "loss": 0.1948, "step": 50 }, { "epoch": 0.24757281553398058, "grad_norm": 6.098858386818918, "learning_rate": 9.626659189190852e-06, "loss": 1.3556, "step": 51 }, { "epoch": 0.2524271844660194, "grad_norm": 3.2961565474058565, "learning_rate": 9.612068988375898e-06, "loss": 0.1675, "step": 52 }, { "epoch": 0.25728155339805825, "grad_norm": 4.3986677165375525, "learning_rate": 9.597210624469288e-06, "loss": 0.1971, "step": 53 }, { "epoch": 0.2621359223300971, "grad_norm": 3.177129834284871, "learning_rate": 9.582084961392358e-06, "loss": 0.1439, "step": 54 }, { "epoch": 0.2669902912621359, "grad_norm": 3.3475437780719637, "learning_rate": 9.566692878608229e-06, "loss": 0.1618, "step": 55 }, { "epoch": 0.27184466019417475, "grad_norm": 3.8249351827001177, "learning_rate": 9.551035271070665e-06, "loss": 0.2095, "step": 56 }, { "epoch": 0.2766990291262136, "grad_norm": 3.7494052477874003, "learning_rate": 9.53511304917204e-06, "loss": 0.1899, "step": 57 }, { "epoch": 0.2815533980582524, "grad_norm": 3.137113053607151, "learning_rate": 9.51892713869041e-06, "loss": 0.1361, "step": 58 }, { "epoch": 0.28640776699029125, "grad_norm": 4.154996879718851, "learning_rate": 9.502478480735678e-06, "loss": 0.1873, "step": 59 }, { "epoch": 0.2912621359223301, "grad_norm": 3.8345434030006658, "learning_rate": 9.485768031694872e-06, "loss": 0.1867, "step": 60 }, { "epoch": 0.2961165048543689, "grad_norm": 4.01375505704675, "learning_rate": 9.468796763176549e-06, "loss": 0.2054, "step": 61 }, { "epoch": 0.30097087378640774, "grad_norm": 4.06144310993101, "learning_rate": 9.45156566195429e-06, "loss": 0.1571, "step": 62 }, { "epoch": 0.3058252427184466, "grad_norm": 3.792468878802408, "learning_rate": 9.43407572990933e-06, "loss": 0.1837, "step": 63 }, { "epoch": 0.3106796116504854, "grad_norm": 3.648120070990038, "learning_rate": 9.416327983972304e-06, "loss": 0.1938, "step": 64 }, { "epoch": 0.3155339805825243, "grad_norm": 3.489437914184596, "learning_rate": 9.398323456064124e-06, "loss": 0.2241, "step": 65 }, { "epoch": 0.32038834951456313, "grad_norm": 3.374340511480333, "learning_rate": 9.380063193035968e-06, "loss": 0.177, "step": 66 }, { "epoch": 0.32524271844660196, "grad_norm": 3.264598449702114, "learning_rate": 9.361548256608421e-06, "loss": 0.1797, "step": 67 }, { "epoch": 0.3300970873786408, "grad_norm": 3.966830853033163, "learning_rate": 9.342779723309746e-06, "loss": 0.2554, "step": 68 }, { "epoch": 0.33495145631067963, "grad_norm": 3.420409800935627, "learning_rate": 9.323758684413272e-06, "loss": 0.1478, "step": 69 }, { "epoch": 0.33980582524271846, "grad_norm": 3.7130637493387324, "learning_rate": 9.304486245873973e-06, "loss": 0.1751, "step": 70 }, { "epoch": 0.3446601941747573, "grad_norm": 3.5828005486461563, "learning_rate": 9.284963528264133e-06, "loss": 0.1823, "step": 71 }, { "epoch": 0.34951456310679613, "grad_norm": 3.3855623884926134, "learning_rate": 9.26519166670821e-06, "loss": 0.1685, "step": 72 }, { "epoch": 0.35436893203883496, "grad_norm": 8.968308123292674, "learning_rate": 9.24517181081683e-06, "loss": 2.1169, "step": 73 }, { "epoch": 0.3592233009708738, "grad_norm": 3.4944633320992358, "learning_rate": 9.22490512461995e-06, "loss": 0.1636, "step": 74 }, { "epoch": 0.3640776699029126, "grad_norm": 4.197357025299537, "learning_rate": 9.204392786499168e-06, "loss": 0.2401, "step": 75 }, { "epoch": 0.36893203883495146, "grad_norm": 3.3051744285672373, "learning_rate": 9.183635989119211e-06, "loss": 0.1641, "step": 76 }, { "epoch": 0.3737864077669903, "grad_norm": 3.6322680235984235, "learning_rate": 9.162635939358593e-06, "loss": 0.1614, "step": 77 }, { "epoch": 0.3786407766990291, "grad_norm": 3.2637668132144895, "learning_rate": 9.141393858239435e-06, "loss": 0.1459, "step": 78 }, { "epoch": 0.38349514563106796, "grad_norm": 3.2541730866975893, "learning_rate": 9.119910980856477e-06, "loss": 0.1804, "step": 79 }, { "epoch": 0.3883495145631068, "grad_norm": 3.2213080042311586, "learning_rate": 9.098188556305262e-06, "loss": 0.19, "step": 80 }, { "epoch": 0.3932038834951456, "grad_norm": 3.4206478733768075, "learning_rate": 9.076227847609513e-06, "loss": 0.144, "step": 81 }, { "epoch": 0.39805825242718446, "grad_norm": 2.8054401115428824, "learning_rate": 9.054030131647682e-06, "loss": 0.1541, "step": 82 }, { "epoch": 0.4029126213592233, "grad_norm": 3.833189307216376, "learning_rate": 9.031596699078727e-06, "loss": 0.231, "step": 83 }, { "epoch": 0.4077669902912621, "grad_norm": 3.692036642881131, "learning_rate": 9.008928854267054e-06, "loss": 0.1729, "step": 84 }, { "epoch": 0.41262135922330095, "grad_norm": 3.23541497427633, "learning_rate": 8.986027915206686e-06, "loss": 0.1286, "step": 85 }, { "epoch": 0.4174757281553398, "grad_norm": 4.0009005067420365, "learning_rate": 8.962895213444618e-06, "loss": 0.1922, "step": 86 }, { "epoch": 0.4223300970873786, "grad_norm": 3.371659427266, "learning_rate": 8.939532094003409e-06, "loss": 1.6075, "step": 87 }, { "epoch": 0.42718446601941745, "grad_norm": 4.543078324073699, "learning_rate": 8.91593991530297e-06, "loss": 0.1903, "step": 88 }, { "epoch": 0.4320388349514563, "grad_norm": 5.581237410035587, "learning_rate": 8.892120049081577e-06, "loss": 0.2364, "step": 89 }, { "epoch": 0.4368932038834951, "grad_norm": 3.4788239166280337, "learning_rate": 8.868073880316125e-06, "loss": 0.2073, "step": 90 }, { "epoch": 0.441747572815534, "grad_norm": 3.4847904706068893, "learning_rate": 8.843802807141584e-06, "loss": 0.1641, "step": 91 }, { "epoch": 0.44660194174757284, "grad_norm": 4.376363674830701, "learning_rate": 8.819308240769726e-06, "loss": 0.2238, "step": 92 }, { "epoch": 0.45145631067961167, "grad_norm": 3.269073216227844, "learning_rate": 8.794591605407047e-06, "loss": 0.1974, "step": 93 }, { "epoch": 0.4563106796116505, "grad_norm": 4.3052039894235135, "learning_rate": 8.769654338171986e-06, "loss": 0.2162, "step": 94 }, { "epoch": 0.46116504854368934, "grad_norm": 3.300951688264894, "learning_rate": 8.744497889011344e-06, "loss": 0.1779, "step": 95 }, { "epoch": 0.46601941747572817, "grad_norm": 3.1987714308242885, "learning_rate": 8.71912372061598e-06, "loss": 0.1827, "step": 96 }, { "epoch": 0.470873786407767, "grad_norm": 2.8017077028359885, "learning_rate": 8.693533308335786e-06, "loss": 0.148, "step": 97 }, { "epoch": 0.47572815533980584, "grad_norm": 3.102368312031283, "learning_rate": 8.667728140093876e-06, "loss": 0.2068, "step": 98 }, { "epoch": 0.48058252427184467, "grad_norm": 3.6508180598366695, "learning_rate": 8.641709716300092e-06, "loss": 0.2029, "step": 99 }, { "epoch": 0.4854368932038835, "grad_norm": 3.3950171740747166, "learning_rate": 8.615479549763756e-06, "loss": 1.8884, "step": 100 }, { "epoch": 0.49029126213592233, "grad_norm": 3.1312849938657896, "learning_rate": 8.589039165605716e-06, "loss": 0.1537, "step": 101 }, { "epoch": 0.49514563106796117, "grad_norm": 3.5801315817647232, "learning_rate": 8.56239010116966e-06, "loss": 0.1824, "step": 102 }, { "epoch": 0.5, "grad_norm": 3.546534300447041, "learning_rate": 8.535533905932739e-06, "loss": 0.1804, "step": 103 }, { "epoch": 0.5048543689320388, "grad_norm": 3.2877479715730313, "learning_rate": 8.508472141415468e-06, "loss": 0.1617, "step": 104 }, { "epoch": 0.5097087378640777, "grad_norm": 3.5584173121991323, "learning_rate": 8.481206381090934e-06, "loss": 0.1887, "step": 105 }, { "epoch": 0.5145631067961165, "grad_norm": 3.805569430447853, "learning_rate": 8.453738210293316e-06, "loss": 0.1721, "step": 106 }, { "epoch": 0.5194174757281553, "grad_norm": 3.881708238229782, "learning_rate": 8.426069226125695e-06, "loss": 0.1838, "step": 107 }, { "epoch": 0.5242718446601942, "grad_norm": 3.98671495838238, "learning_rate": 8.398201037367202e-06, "loss": 0.1961, "step": 108 }, { "epoch": 0.529126213592233, "grad_norm": 2.869964566560864, "learning_rate": 8.370135264379475e-06, "loss": 0.1474, "step": 109 }, { "epoch": 0.5339805825242718, "grad_norm": 3.3720637127767605, "learning_rate": 8.341873539012443e-06, "loss": 0.1704, "step": 110 }, { "epoch": 0.5388349514563107, "grad_norm": 3.3436728179491673, "learning_rate": 8.313417504509446e-06, "loss": 0.151, "step": 111 }, { "epoch": 0.5436893203883495, "grad_norm": 3.1939397858342167, "learning_rate": 8.284768815411693e-06, "loss": 0.164, "step": 112 }, { "epoch": 0.5485436893203883, "grad_norm": 3.9497595827371903, "learning_rate": 8.255929137462049e-06, "loss": 0.1844, "step": 113 }, { "epoch": 0.5533980582524272, "grad_norm": 3.6900776204954093, "learning_rate": 8.226900147508205e-06, "loss": 0.1726, "step": 114 }, { "epoch": 0.558252427184466, "grad_norm": 3.416053446028884, "learning_rate": 8.197683533405156e-06, "loss": 0.1651, "step": 115 }, { "epoch": 0.5631067961165048, "grad_norm": 3.830007646061756, "learning_rate": 8.168280993917078e-06, "loss": 0.2018, "step": 116 }, { "epoch": 0.5679611650485437, "grad_norm": 3.6356803944567706, "learning_rate": 8.138694238618543e-06, "loss": 0.186, "step": 117 }, { "epoch": 0.5728155339805825, "grad_norm": 3.268566324515523, "learning_rate": 8.108924987795137e-06, "loss": 0.1807, "step": 118 }, { "epoch": 0.5776699029126213, "grad_norm": 3.0731122010223157, "learning_rate": 8.078974972343414e-06, "loss": 0.1385, "step": 119 }, { "epoch": 0.5825242718446602, "grad_norm": 3.506409488780749, "learning_rate": 8.048845933670274e-06, "loss": 0.1876, "step": 120 }, { "epoch": 0.587378640776699, "grad_norm": 3.0091035344268167, "learning_rate": 8.01853962359169e-06, "loss": 0.1542, "step": 121 }, { "epoch": 0.5922330097087378, "grad_norm": 4.000336192381524, "learning_rate": 7.988057804230878e-06, "loss": 0.1855, "step": 122 }, { "epoch": 0.5970873786407767, "grad_norm": 2.6774596474593015, "learning_rate": 7.957402247915817e-06, "loss": 0.1398, "step": 123 }, { "epoch": 0.6019417475728155, "grad_norm": 3.342400785474733, "learning_rate": 7.92657473707621e-06, "loss": 0.1571, "step": 124 }, { "epoch": 0.6067961165048543, "grad_norm": 2.839224634847776, "learning_rate": 7.895577064139847e-06, "loss": 0.2838, "step": 125 }, { "epoch": 0.6116504854368932, "grad_norm": 3.265216498891963, "learning_rate": 7.864411031428379e-06, "loss": 0.1605, "step": 126 }, { "epoch": 0.616504854368932, "grad_norm": 2.826555903641288, "learning_rate": 7.833078451052537e-06, "loss": 0.1552, "step": 127 }, { "epoch": 0.6213592233009708, "grad_norm": 3.263465403684562, "learning_rate": 7.801581144806752e-06, "loss": 0.1409, "step": 128 }, { "epoch": 0.6262135922330098, "grad_norm": 3.115501404573261, "learning_rate": 7.769920944063244e-06, "loss": 0.1388, "step": 129 }, { "epoch": 0.6310679611650486, "grad_norm": 3.454177176086228, "learning_rate": 7.73809968966554e-06, "loss": 0.1691, "step": 130 }, { "epoch": 0.6359223300970874, "grad_norm": 3.669774425160351, "learning_rate": 7.706119231821423e-06, "loss": 2.0662, "step": 131 }, { "epoch": 0.6407766990291263, "grad_norm": 2.9578717822726994, "learning_rate": 7.673981429995372e-06, "loss": 0.1217, "step": 132 }, { "epoch": 0.6456310679611651, "grad_norm": 3.215506984482298, "learning_rate": 7.641688152800433e-06, "loss": 0.1641, "step": 133 }, { "epoch": 0.6504854368932039, "grad_norm": 3.5261600831309683, "learning_rate": 7.609241277889583e-06, "loss": 0.1581, "step": 134 }, { "epoch": 0.6553398058252428, "grad_norm": 3.348004239497448, "learning_rate": 7.5766426918465455e-06, "loss": 0.1655, "step": 135 }, { "epoch": 0.6601941747572816, "grad_norm": 3.463003474785134, "learning_rate": 7.5438942900761035e-06, "loss": 0.179, "step": 136 }, { "epoch": 0.6650485436893204, "grad_norm": 3.299946611300431, "learning_rate": 7.51099797669389e-06, "loss": 0.1838, "step": 137 }, { "epoch": 0.6699029126213593, "grad_norm": 3.734578866130712, "learning_rate": 7.477955664415678e-06, "loss": 0.2121, "step": 138 }, { "epoch": 0.6747572815533981, "grad_norm": 3.104951473650513, "learning_rate": 7.444769274446168e-06, "loss": 0.1522, "step": 139 }, { "epoch": 0.6796116504854369, "grad_norm": 3.133143645012315, "learning_rate": 7.411440736367281e-06, "loss": 0.158, "step": 140 }, { "epoch": 0.6844660194174758, "grad_norm": 3.059272264008987, "learning_rate": 7.377971988025964e-06, "loss": 0.1431, "step": 141 }, { "epoch": 0.6893203883495146, "grad_norm": 3.4811771159052127, "learning_rate": 7.3443649754215175e-06, "loss": 0.1609, "step": 142 }, { "epoch": 0.6941747572815534, "grad_norm": 3.85738998682577, "learning_rate": 7.310621652592449e-06, "loss": 0.1537, "step": 143 }, { "epoch": 0.6990291262135923, "grad_norm": 3.4019001310027877, "learning_rate": 7.276743981502856e-06, "loss": 0.161, "step": 144 }, { "epoch": 0.7038834951456311, "grad_norm": 3.396761694989364, "learning_rate": 7.242733931928352e-06, "loss": 1.968, "step": 145 }, { "epoch": 0.7087378640776699, "grad_norm": 3.0749985922565415, "learning_rate": 7.208593481341536e-06, "loss": 0.164, "step": 146 }, { "epoch": 0.7135922330097088, "grad_norm": 3.1539841039599077, "learning_rate": 7.1743246147970095e-06, "loss": 0.156, "step": 147 }, { "epoch": 0.7184466019417476, "grad_norm": 3.4892734050571677, "learning_rate": 7.139929324815965e-06, "loss": 0.1884, "step": 148 }, { "epoch": 0.7233009708737864, "grad_norm": 2.7320915520428635, "learning_rate": 7.105409611270332e-06, "loss": 0.1219, "step": 149 }, { "epoch": 0.7281553398058253, "grad_norm": 3.0178546824462114, "learning_rate": 7.070767481266493e-06, "loss": 0.1732, "step": 150 }, { "epoch": 0.7330097087378641, "grad_norm": 2.8056474690169986, "learning_rate": 7.036004949028587e-06, "loss": 0.1481, "step": 151 }, { "epoch": 0.7378640776699029, "grad_norm": 3.10021388569035, "learning_rate": 7.00112403578139e-06, "loss": 0.1673, "step": 152 }, { "epoch": 0.7427184466019418, "grad_norm": 3.26753532587258, "learning_rate": 6.9661267696328015e-06, "loss": 0.1883, "step": 153 }, { "epoch": 0.7475728155339806, "grad_norm": 3.4255182899390033, "learning_rate": 6.931015185455915e-06, "loss": 0.2046, "step": 154 }, { "epoch": 0.7524271844660194, "grad_norm": 3.636720170211082, "learning_rate": 6.895791324770702e-06, "loss": 0.2068, "step": 155 }, { "epoch": 0.7572815533980582, "grad_norm": 3.053662406730595, "learning_rate": 6.860457235625322e-06, "loss": 0.169, "step": 156 }, { "epoch": 0.7621359223300971, "grad_norm": 3.0420805095324686, "learning_rate": 6.825014972477024e-06, "loss": 0.1662, "step": 157 }, { "epoch": 0.7669902912621359, "grad_norm": 3.5230733226696898, "learning_rate": 6.7894665960727105e-06, "loss": 0.2034, "step": 158 }, { "epoch": 0.7718446601941747, "grad_norm": 3.891671449744887, "learning_rate": 6.7538141733291e-06, "loss": 0.2038, "step": 159 }, { "epoch": 0.7766990291262136, "grad_norm": 4.12261748913082, "learning_rate": 6.7180597772125665e-06, "loss": 0.1852, "step": 160 }, { "epoch": 0.7815533980582524, "grad_norm": 3.0068851640498195, "learning_rate": 6.682205486618592e-06, "loss": 0.1597, "step": 161 }, { "epoch": 0.7864077669902912, "grad_norm": 3.5271313218773885, "learning_rate": 6.646253386250909e-06, "loss": 0.2022, "step": 162 }, { "epoch": 0.7912621359223301, "grad_norm": 3.777114140168497, "learning_rate": 6.610205566500272e-06, "loss": 0.2029, "step": 163 }, { "epoch": 0.7961165048543689, "grad_norm": 3.2070899922727127, "learning_rate": 6.574064123322925e-06, "loss": 0.1883, "step": 164 }, { "epoch": 0.8009708737864077, "grad_norm": 2.856172766834049, "learning_rate": 6.537831158118733e-06, "loss": 0.1323, "step": 165 }, { "epoch": 0.8058252427184466, "grad_norm": 3.2401941234963023, "learning_rate": 6.50150877760899e-06, "loss": 0.1786, "step": 166 }, { "epoch": 0.8106796116504854, "grad_norm": 3.3661235424780385, "learning_rate": 6.465099093713944e-06, "loss": 0.1753, "step": 167 }, { "epoch": 0.8155339805825242, "grad_norm": 2.688408919315557, "learning_rate": 6.42860422342998e-06, "loss": 0.1516, "step": 168 }, { "epoch": 0.8203883495145631, "grad_norm": 3.7810659287217723, "learning_rate": 6.392026288706549e-06, "loss": 0.1481, "step": 169 }, { "epoch": 0.8252427184466019, "grad_norm": 3.685444342996392, "learning_rate": 6.3553674163227786e-06, "loss": 0.1731, "step": 170 }, { "epoch": 0.8300970873786407, "grad_norm": 2.946846864594844, "learning_rate": 6.318629737763818e-06, "loss": 0.1609, "step": 171 }, { "epoch": 0.8349514563106796, "grad_norm": 3.8276099009344824, "learning_rate": 6.281815389096903e-06, "loss": 0.1881, "step": 172 }, { "epoch": 0.8398058252427184, "grad_norm": 3.303535702159252, "learning_rate": 6.244926510847162e-06, "loss": 0.1479, "step": 173 }, { "epoch": 0.8446601941747572, "grad_norm": 3.807883566694266, "learning_rate": 6.207965247873151e-06, "loss": 0.1903, "step": 174 }, { "epoch": 0.8495145631067961, "grad_norm": 2.911567051543024, "learning_rate": 6.1709337492421515e-06, "loss": 0.1295, "step": 175 }, { "epoch": 0.8543689320388349, "grad_norm": 3.2046177093058166, "learning_rate": 6.133834168105206e-06, "loss": 0.1568, "step": 176 }, { "epoch": 0.8592233009708737, "grad_norm": 3.3349281673831803, "learning_rate": 6.096668661571934e-06, "loss": 0.1702, "step": 177 }, { "epoch": 0.8640776699029126, "grad_norm": 3.9332514492121096, "learning_rate": 6.0594393905851065e-06, "loss": 0.2129, "step": 178 }, { "epoch": 0.8689320388349514, "grad_norm": 3.6828564033007316, "learning_rate": 6.0221485197949995e-06, "loss": 0.1777, "step": 179 }, { "epoch": 0.8737864077669902, "grad_norm": 3.9344402235799714, "learning_rate": 5.9847982174335314e-06, "loss": 0.218, "step": 180 }, { "epoch": 0.8786407766990292, "grad_norm": 3.437911020577905, "learning_rate": 5.9473906551881985e-06, "loss": 0.1915, "step": 181 }, { "epoch": 0.883495145631068, "grad_norm": 3.584257218638752, "learning_rate": 5.9099280080758085e-06, "loss": 0.2143, "step": 182 }, { "epoch": 0.8883495145631068, "grad_norm": 3.3884751449077846, "learning_rate": 5.872412454315999e-06, "loss": 0.1848, "step": 183 }, { "epoch": 0.8932038834951457, "grad_norm": 3.847696159285092, "learning_rate": 5.834846175204612e-06, "loss": 0.1914, "step": 184 }, { "epoch": 0.8980582524271845, "grad_norm": 3.4294270132408733, "learning_rate": 5.797231354986842e-06, "loss": 0.1733, "step": 185 }, { "epoch": 0.9029126213592233, "grad_norm": 2.7006091171005244, "learning_rate": 5.759570180730255e-06, "loss": 0.1786, "step": 186 }, { "epoch": 0.9077669902912622, "grad_norm": 3.1518913649529128, "learning_rate": 5.721864842197612e-06, "loss": 0.1569, "step": 187 }, { "epoch": 0.912621359223301, "grad_norm": 3.9310146604996876, "learning_rate": 5.684117531719552e-06, "loss": 0.2194, "step": 188 }, { "epoch": 0.9174757281553398, "grad_norm": 3.6243954425466383, "learning_rate": 5.646330444067121e-06, "loss": 0.1515, "step": 189 }, { "epoch": 0.9223300970873787, "grad_norm": 2.9597266924343373, "learning_rate": 5.608505776324158e-06, "loss": 0.1631, "step": 190 }, { "epoch": 0.9271844660194175, "grad_norm": 3.29651731345373, "learning_rate": 5.570645727759558e-06, "loss": 0.1762, "step": 191 }, { "epoch": 0.9320388349514563, "grad_norm": 3.02642514409216, "learning_rate": 5.532752499699381e-06, "loss": 0.1794, "step": 192 }, { "epoch": 0.9368932038834952, "grad_norm": 3.1368920826260736, "learning_rate": 5.494828295398874e-06, "loss": 0.178, "step": 193 }, { "epoch": 0.941747572815534, "grad_norm": 2.9748663003734457, "learning_rate": 5.456875319914355e-06, "loss": 0.1558, "step": 194 }, { "epoch": 0.9466019417475728, "grad_norm": 3.447694232964055, "learning_rate": 5.4188957799750145e-06, "loss": 0.143, "step": 195 }, { "epoch": 0.9514563106796117, "grad_norm": 2.9468105285885122, "learning_rate": 5.380891883854591e-06, "loss": 0.1585, "step": 196 }, { "epoch": 0.9563106796116505, "grad_norm": 2.796739428227403, "learning_rate": 5.34286584124299e-06, "loss": 0.1345, "step": 197 }, { "epoch": 0.9611650485436893, "grad_norm": 3.0833816121492337, "learning_rate": 5.304819863117796e-06, "loss": 0.1247, "step": 198 }, { "epoch": 0.9660194174757282, "grad_norm": 3.0876458359936496, "learning_rate": 5.266756161615719e-06, "loss": 0.164, "step": 199 }, { "epoch": 0.970873786407767, "grad_norm": 3.4454095679040484, "learning_rate": 5.228676949903974e-06, "loss": 0.1681, "step": 200 }, { "epoch": 0.9757281553398058, "grad_norm": 3.661107038218155, "learning_rate": 5.190584442051594e-06, "loss": 0.2034, "step": 201 }, { "epoch": 0.9805825242718447, "grad_norm": 2.9781763427858783, "learning_rate": 5.1524808529007075e-06, "loss": 2.0615, "step": 202 }, { "epoch": 0.9854368932038835, "grad_norm": 3.4144794700513006, "learning_rate": 5.114368397937744e-06, "loss": 0.18, "step": 203 }, { "epoch": 0.9902912621359223, "grad_norm": 2.891912771085034, "learning_rate": 5.07624929316463e-06, "loss": 0.1692, "step": 204 }, { "epoch": 0.9951456310679612, "grad_norm": 3.940859743167215, "learning_rate": 5.038125754969933e-06, "loss": 0.1597, "step": 205 }, { "epoch": 1.0, "grad_norm": 2.114078403400398, "learning_rate": 5e-06, "loss": 0.0509, "step": 206 }, { "epoch": 1.0048543689320388, "grad_norm": 2.4861837147789907, "learning_rate": 4.9618742450300675e-06, "loss": 0.0947, "step": 207 }, { "epoch": 1.0097087378640777, "grad_norm": 2.574928651437252, "learning_rate": 4.923750706835371e-06, "loss": 0.0877, "step": 208 }, { "epoch": 1.0145631067961165, "grad_norm": 2.390628942600892, "learning_rate": 4.8856316020622564e-06, "loss": 0.0849, "step": 209 }, { "epoch": 1.0194174757281553, "grad_norm": 2.0965587115046147, "learning_rate": 4.847519147099294e-06, "loss": 0.0691, "step": 210 }, { "epoch": 1.0242718446601942, "grad_norm": 2.4149356959145742, "learning_rate": 4.809415557948407e-06, "loss": 0.095, "step": 211 }, { "epoch": 1.029126213592233, "grad_norm": 2.235598621225836, "learning_rate": 4.771323050096028e-06, "loss": 0.0836, "step": 212 }, { "epoch": 1.0339805825242718, "grad_norm": 2.777474574971205, "learning_rate": 4.733243838384282e-06, "loss": 0.0846, "step": 213 }, { "epoch": 1.0388349514563107, "grad_norm": 2.7422183722820437, "learning_rate": 4.6951801368822055e-06, "loss": 0.0886, "step": 214 }, { "epoch": 1.0436893203883495, "grad_norm": 3.583667258228157, "learning_rate": 4.6571341587570114e-06, "loss": 0.0853, "step": 215 }, { "epoch": 1.0485436893203883, "grad_norm": 2.1429438147133983, "learning_rate": 4.619108116145411e-06, "loss": 0.0709, "step": 216 }, { "epoch": 1.0533980582524272, "grad_norm": 2.638520623375338, "learning_rate": 4.581104220024988e-06, "loss": 0.0918, "step": 217 }, { "epoch": 1.058252427184466, "grad_norm": 2.4373654485190546, "learning_rate": 4.5431246800856455e-06, "loss": 0.0659, "step": 218 }, { "epoch": 1.0631067961165048, "grad_norm": 2.954470745196081, "learning_rate": 4.505171704601128e-06, "loss": 0.0865, "step": 219 }, { "epoch": 1.0679611650485437, "grad_norm": 2.5357819989918675, "learning_rate": 4.467247500300621e-06, "loss": 0.0639, "step": 220 }, { "epoch": 1.0728155339805825, "grad_norm": 3.196945279517692, "learning_rate": 4.4293542722404435e-06, "loss": 0.075, "step": 221 }, { "epoch": 1.0776699029126213, "grad_norm": 3.602207511683068, "learning_rate": 4.391494223675843e-06, "loss": 0.0877, "step": 222 }, { "epoch": 1.0825242718446602, "grad_norm": 3.072945774218816, "learning_rate": 4.3536695559328816e-06, "loss": 0.0886, "step": 223 }, { "epoch": 1.087378640776699, "grad_norm": 2.9327628358781443, "learning_rate": 4.31588246828045e-06, "loss": 0.0779, "step": 224 }, { "epoch": 1.0922330097087378, "grad_norm": 3.884559725530265, "learning_rate": 4.278135157802389e-06, "loss": 0.0957, "step": 225 }, { "epoch": 1.0970873786407767, "grad_norm": 2.638727931000126, "learning_rate": 4.240429819269746e-06, "loss": 0.0578, "step": 226 }, { "epoch": 1.1019417475728155, "grad_norm": 3.1117784042872283, "learning_rate": 4.20276864501316e-06, "loss": 0.0692, "step": 227 }, { "epoch": 1.1067961165048543, "grad_norm": 2.7783624029964757, "learning_rate": 4.165153824795391e-06, "loss": 0.0768, "step": 228 }, { "epoch": 1.1116504854368932, "grad_norm": 2.594503486377878, "learning_rate": 4.127587545684002e-06, "loss": 0.0669, "step": 229 }, { "epoch": 1.116504854368932, "grad_norm": 2.929448813987237, "learning_rate": 4.090071991924194e-06, "loss": 0.0756, "step": 230 }, { "epoch": 1.1213592233009708, "grad_norm": 2.6878856077703426, "learning_rate": 4.052609344811802e-06, "loss": 1.6006, "step": 231 }, { "epoch": 1.1262135922330097, "grad_norm": 2.9800498201414296, "learning_rate": 4.015201782566471e-06, "loss": 0.084, "step": 232 }, { "epoch": 1.1310679611650485, "grad_norm": 2.945464576525122, "learning_rate": 3.977851480205003e-06, "loss": 0.0831, "step": 233 }, { "epoch": 1.1359223300970873, "grad_norm": 2.228512930491437, "learning_rate": 3.940560609414894e-06, "loss": 0.0563, "step": 234 }, { "epoch": 1.1407766990291262, "grad_norm": 2.407897491051693, "learning_rate": 3.903331338428067e-06, "loss": 0.0633, "step": 235 }, { "epoch": 1.145631067961165, "grad_norm": 2.4538104943960724, "learning_rate": 3.866165831894796e-06, "loss": 0.0602, "step": 236 }, { "epoch": 1.1504854368932038, "grad_norm": 2.526844108676813, "learning_rate": 3.829066250757851e-06, "loss": 0.0772, "step": 237 }, { "epoch": 1.1553398058252426, "grad_norm": 3.0770252354322003, "learning_rate": 3.7920347521268514e-06, "loss": 0.0761, "step": 238 }, { "epoch": 1.1601941747572815, "grad_norm": 2.189508386492239, "learning_rate": 3.7550734891528413e-06, "loss": 1.7307, "step": 239 }, { "epoch": 1.1650485436893203, "grad_norm": 2.9398466534526513, "learning_rate": 3.7181846109031007e-06, "loss": 0.0761, "step": 240 }, { "epoch": 1.1699029126213591, "grad_norm": 2.746101050683826, "learning_rate": 3.6813702622361858e-06, "loss": 0.0847, "step": 241 }, { "epoch": 1.174757281553398, "grad_norm": 2.7332263146255382, "learning_rate": 3.6446325836772244e-06, "loss": 0.0653, "step": 242 }, { "epoch": 1.1796116504854368, "grad_norm": 2.7190442575382208, "learning_rate": 3.6079737112934533e-06, "loss": 0.0789, "step": 243 }, { "epoch": 1.1844660194174756, "grad_norm": 2.658390418475969, "learning_rate": 3.5713957765700224e-06, "loss": 0.0603, "step": 244 }, { "epoch": 1.1893203883495145, "grad_norm": 3.9381394273176276, "learning_rate": 3.5349009062860586e-06, "loss": 0.0811, "step": 245 }, { "epoch": 1.1941747572815533, "grad_norm": 3.052172225803538, "learning_rate": 3.4984912223910105e-06, "loss": 0.0702, "step": 246 }, { "epoch": 1.1990291262135921, "grad_norm": 3.0456430643875625, "learning_rate": 3.46216884188127e-06, "loss": 0.0784, "step": 247 }, { "epoch": 1.203883495145631, "grad_norm": 2.5049847942964276, "learning_rate": 3.425935876677077e-06, "loss": 0.0656, "step": 248 }, { "epoch": 1.2087378640776698, "grad_norm": 3.3960154571948, "learning_rate": 3.38979443349973e-06, "loss": 1.9855, "step": 249 }, { "epoch": 1.2135922330097086, "grad_norm": 3.2720834167712214, "learning_rate": 3.3537466137490937e-06, "loss": 0.0577, "step": 250 }, { "epoch": 1.2184466019417475, "grad_norm": 2.481707072834296, "learning_rate": 3.3177945133814093e-06, "loss": 0.0704, "step": 251 }, { "epoch": 1.2233009708737863, "grad_norm": 3.154258406225022, "learning_rate": 3.2819402227874364e-06, "loss": 0.0873, "step": 252 }, { "epoch": 1.2281553398058254, "grad_norm": 3.684874510102613, "learning_rate": 3.2461858266709017e-06, "loss": 0.0717, "step": 253 }, { "epoch": 1.233009708737864, "grad_norm": 2.2393770842849205, "learning_rate": 3.2105334039272924e-06, "loss": 0.0712, "step": 254 }, { "epoch": 1.237864077669903, "grad_norm": 2.5232811881585233, "learning_rate": 3.1749850275229777e-06, "loss": 0.059, "step": 255 }, { "epoch": 1.2427184466019416, "grad_norm": 2.4330838257815612, "learning_rate": 3.1395427643746802e-06, "loss": 0.0665, "step": 256 }, { "epoch": 1.2475728155339807, "grad_norm": 2.6008302295100245, "learning_rate": 3.1042086752292995e-06, "loss": 0.0714, "step": 257 }, { "epoch": 1.2524271844660193, "grad_norm": 2.508640650867831, "learning_rate": 3.068984814544087e-06, "loss": 0.0881, "step": 258 }, { "epoch": 1.2572815533980584, "grad_norm": 2.9570104245960014, "learning_rate": 3.0338732303671993e-06, "loss": 0.0725, "step": 259 }, { "epoch": 1.262135922330097, "grad_norm": 2.8322291333835135, "learning_rate": 2.99887596421861e-06, "loss": 0.0779, "step": 260 }, { "epoch": 1.266990291262136, "grad_norm": 3.4301825184788415, "learning_rate": 2.9639950509714138e-06, "loss": 0.1031, "step": 261 }, { "epoch": 1.2718446601941746, "grad_norm": 2.767528223153958, "learning_rate": 2.929232518733507e-06, "loss": 1.7571, "step": 262 }, { "epoch": 1.2766990291262137, "grad_norm": 2.5005755262187788, "learning_rate": 2.8945903887296686e-06, "loss": 0.0628, "step": 263 }, { "epoch": 1.2815533980582523, "grad_norm": 3.101661943932367, "learning_rate": 2.860070675184036e-06, "loss": 0.0819, "step": 264 }, { "epoch": 1.2864077669902914, "grad_norm": 3.1691737838498906, "learning_rate": 2.8256753852029917e-06, "loss": 0.0959, "step": 265 }, { "epoch": 1.29126213592233, "grad_norm": 3.343426992113499, "learning_rate": 2.7914065186584637e-06, "loss": 0.0853, "step": 266 }, { "epoch": 1.296116504854369, "grad_norm": 2.653786851479733, "learning_rate": 2.757266068071648e-06, "loss": 0.0711, "step": 267 }, { "epoch": 1.3009708737864076, "grad_norm": 3.6695447681004953, "learning_rate": 2.7232560184971437e-06, "loss": 0.0925, "step": 268 }, { "epoch": 1.3058252427184467, "grad_norm": 2.651580917610274, "learning_rate": 2.689378347407553e-06, "loss": 0.0733, "step": 269 }, { "epoch": 1.3106796116504853, "grad_norm": 2.837228186908167, "learning_rate": 2.6556350245784833e-06, "loss": 1.3862, "step": 270 }, { "epoch": 1.3155339805825244, "grad_norm": 2.744275874625859, "learning_rate": 2.6220280119740376e-06, "loss": 0.0802, "step": 271 }, { "epoch": 1.3203883495145632, "grad_norm": 2.7150857011500733, "learning_rate": 2.588559263632719e-06, "loss": 0.0881, "step": 272 }, { "epoch": 1.325242718446602, "grad_norm": 2.923244006407607, "learning_rate": 2.555230725553832e-06, "loss": 0.0695, "step": 273 }, { "epoch": 1.3300970873786409, "grad_norm": 2.648842158951213, "learning_rate": 2.522044335584322e-06, "loss": 0.0808, "step": 274 }, { "epoch": 1.3349514563106797, "grad_norm": 3.46448902282436, "learning_rate": 2.489002023306112e-06, "loss": 0.1095, "step": 275 }, { "epoch": 1.3398058252427185, "grad_norm": 3.765519769264312, "learning_rate": 2.4561057099238973e-06, "loss": 0.124, "step": 276 }, { "epoch": 1.3446601941747574, "grad_norm": 4.120315428329695, "learning_rate": 2.423357308153454e-06, "loss": 0.0726, "step": 277 }, { "epoch": 1.3495145631067962, "grad_norm": 2.603195360336072, "learning_rate": 2.390758722110418e-06, "loss": 0.0746, "step": 278 }, { "epoch": 1.354368932038835, "grad_norm": 2.3116504612959927, "learning_rate": 2.358311847199567e-06, "loss": 0.067, "step": 279 }, { "epoch": 1.3592233009708738, "grad_norm": 2.510814292579119, "learning_rate": 2.3260185700046295e-06, "loss": 0.0553, "step": 280 }, { "epoch": 1.3640776699029127, "grad_norm": 2.6478794602920432, "learning_rate": 2.2938807681785764e-06, "loss": 0.069, "step": 281 }, { "epoch": 1.3689320388349515, "grad_norm": 2.7971908923982114, "learning_rate": 2.2619003103344607e-06, "loss": 0.1027, "step": 282 }, { "epoch": 1.3737864077669903, "grad_norm": 2.6161854307520906, "learning_rate": 2.2300790559367553e-06, "loss": 0.0699, "step": 283 }, { "epoch": 1.3786407766990292, "grad_norm": 2.634458727413624, "learning_rate": 2.1984188551932513e-06, "loss": 0.0674, "step": 284 }, { "epoch": 1.383495145631068, "grad_norm": 3.3954408135653167, "learning_rate": 2.166921548947466e-06, "loss": 0.0978, "step": 285 }, { "epoch": 1.3883495145631068, "grad_norm": 3.0988180285059483, "learning_rate": 2.1355889685716225e-06, "loss": 0.0867, "step": 286 }, { "epoch": 1.3932038834951457, "grad_norm": 3.142246921881293, "learning_rate": 2.1044229358601543e-06, "loss": 0.0703, "step": 287 }, { "epoch": 1.3980582524271845, "grad_norm": 2.650846344034233, "learning_rate": 2.0734252629237892e-06, "loss": 0.0659, "step": 288 }, { "epoch": 1.4029126213592233, "grad_norm": 2.668075517191942, "learning_rate": 2.0425977520841837e-06, "loss": 0.0688, "step": 289 }, { "epoch": 1.4077669902912622, "grad_norm": 2.2829588717500076, "learning_rate": 2.011942195769122e-06, "loss": 0.0559, "step": 290 }, { "epoch": 1.412621359223301, "grad_norm": 2.3089636771028768, "learning_rate": 1.9814603764083112e-06, "loss": 0.0569, "step": 291 }, { "epoch": 1.4174757281553398, "grad_norm": 3.404110096743085, "learning_rate": 1.9511540663297284e-06, "loss": 0.0898, "step": 292 }, { "epoch": 1.4223300970873787, "grad_norm": 2.4241689478907693, "learning_rate": 1.921025027656587e-06, "loss": 0.0677, "step": 293 }, { "epoch": 1.4271844660194175, "grad_norm": 3.421022845581842, "learning_rate": 1.8910750122048638e-06, "loss": 0.0753, "step": 294 }, { "epoch": 1.4320388349514563, "grad_norm": 2.9505519123559205, "learning_rate": 1.8613057613814584e-06, "loss": 0.0575, "step": 295 }, { "epoch": 1.4368932038834952, "grad_norm": 3.255569595427685, "learning_rate": 1.8317190060829242e-06, "loss": 0.0947, "step": 296 }, { "epoch": 1.441747572815534, "grad_norm": 3.065400843837357, "learning_rate": 1.8023164665948455e-06, "loss": 0.0807, "step": 297 }, { "epoch": 1.4466019417475728, "grad_norm": 2.9590611079634686, "learning_rate": 1.773099852491796e-06, "loss": 0.0736, "step": 298 }, { "epoch": 1.4514563106796117, "grad_norm": 2.3025998916201313, "learning_rate": 1.7440708625379503e-06, "loss": 0.0625, "step": 299 }, { "epoch": 1.4563106796116505, "grad_norm": 3.903839237318337, "learning_rate": 1.7152311845883096e-06, "loss": 0.0842, "step": 300 }, { "epoch": 1.4611650485436893, "grad_norm": 2.4750320274405633, "learning_rate": 1.686582495490554e-06, "loss": 0.0708, "step": 301 }, { "epoch": 1.4660194174757282, "grad_norm": 2.503972370862682, "learning_rate": 1.658126460987558e-06, "loss": 0.0637, "step": 302 }, { "epoch": 1.470873786407767, "grad_norm": 3.3785939083312626, "learning_rate": 1.6298647356205255e-06, "loss": 0.0747, "step": 303 }, { "epoch": 1.4757281553398058, "grad_norm": 2.2222765612234783, "learning_rate": 1.601798962632799e-06, "loss": 0.0597, "step": 304 }, { "epoch": 1.4805825242718447, "grad_norm": 2.446669257372903, "learning_rate": 1.573930773874306e-06, "loss": 0.065, "step": 305 }, { "epoch": 1.4854368932038835, "grad_norm": 2.652465423917927, "learning_rate": 1.5462617897066863e-06, "loss": 0.0712, "step": 306 }, { "epoch": 1.4902912621359223, "grad_norm": 2.4004481423909203, "learning_rate": 1.5187936189090668e-06, "loss": 0.1966, "step": 307 }, { "epoch": 1.4951456310679612, "grad_norm": 2.8096811136447672, "learning_rate": 1.491527858584535e-06, "loss": 0.0755, "step": 308 }, { "epoch": 1.5, "grad_norm": 2.8236825513139565, "learning_rate": 1.4644660940672628e-06, "loss": 0.0955, "step": 309 }, { "epoch": 1.5048543689320388, "grad_norm": 2.710817444163041, "learning_rate": 1.4376098988303406e-06, "loss": 0.0629, "step": 310 }, { "epoch": 1.5097087378640777, "grad_norm": 3.096915505389332, "learning_rate": 1.4109608343942855e-06, "loss": 0.0638, "step": 311 }, { "epoch": 1.5145631067961165, "grad_norm": 2.3241464797551057, "learning_rate": 1.3845204502362442e-06, "loss": 0.0712, "step": 312 }, { "epoch": 1.5194174757281553, "grad_norm": 3.590980478005006, "learning_rate": 1.35829028369991e-06, "loss": 0.0877, "step": 313 }, { "epoch": 1.5242718446601942, "grad_norm": 2.4429554321376723, "learning_rate": 1.3322718599061252e-06, "loss": 0.0568, "step": 314 }, { "epoch": 1.529126213592233, "grad_norm": 3.0929878244984743, "learning_rate": 1.306466691664216e-06, "loss": 0.0818, "step": 315 }, { "epoch": 1.5339805825242718, "grad_norm": 2.441836649677217, "learning_rate": 1.28087627938402e-06, "loss": 0.0686, "step": 316 }, { "epoch": 1.5388349514563107, "grad_norm": 2.85692848721824, "learning_rate": 1.2555021109886589e-06, "loss": 0.0897, "step": 317 }, { "epoch": 1.5436893203883495, "grad_norm": 3.2892259857698822, "learning_rate": 1.2303456618280141e-06, "loss": 0.0793, "step": 318 }, { "epoch": 1.5485436893203883, "grad_norm": 2.586755097767611, "learning_rate": 1.2054083945929534e-06, "loss": 0.0633, "step": 319 }, { "epoch": 1.5533980582524272, "grad_norm": 2.480887665282937, "learning_rate": 1.1806917592302763e-06, "loss": 0.0643, "step": 320 }, { "epoch": 1.558252427184466, "grad_norm": 2.8797900449745115, "learning_rate": 1.1561971928584158e-06, "loss": 0.056, "step": 321 }, { "epoch": 1.5631067961165048, "grad_norm": 2.866817525662025, "learning_rate": 1.1319261196838782e-06, "loss": 0.0839, "step": 322 }, { "epoch": 1.5679611650485437, "grad_norm": 3.862409612419987, "learning_rate": 1.1078799509184246e-06, "loss": 0.097, "step": 323 }, { "epoch": 1.5728155339805825, "grad_norm": 3.247997005248643, "learning_rate": 1.0840600846970333e-06, "loss": 0.0842, "step": 324 }, { "epoch": 1.5776699029126213, "grad_norm": 2.9068905324472274, "learning_rate": 1.0604679059965923e-06, "loss": 0.1058, "step": 325 }, { "epoch": 1.5825242718446602, "grad_norm": 2.8774681950293632, "learning_rate": 1.0371047865553847e-06, "loss": 0.0849, "step": 326 }, { "epoch": 1.587378640776699, "grad_norm": 2.8220546167673857, "learning_rate": 1.0139720847933166e-06, "loss": 0.0626, "step": 327 }, { "epoch": 1.5922330097087378, "grad_norm": 3.229748629712671, "learning_rate": 9.91071145732948e-07, "loss": 0.085, "step": 328 }, { "epoch": 1.5970873786407767, "grad_norm": 3.8285741772219235, "learning_rate": 9.684033009212752e-07, "loss": 0.0922, "step": 329 }, { "epoch": 1.6019417475728155, "grad_norm": 3.1716964433534804, "learning_rate": 9.459698683523205e-07, "loss": 0.0813, "step": 330 }, { "epoch": 1.6067961165048543, "grad_norm": 4.025671520411109, "learning_rate": 9.237721523904891e-07, "loss": 0.1209, "step": 331 }, { "epoch": 1.6116504854368932, "grad_norm": 1.853073997819308, "learning_rate": 9.018114436947373e-07, "loss": 0.0478, "step": 332 }, { "epoch": 1.616504854368932, "grad_norm": 2.7252545212519985, "learning_rate": 8.80089019143524e-07, "loss": 0.0669, "step": 333 }, { "epoch": 1.6213592233009708, "grad_norm": 2.688094491542211, "learning_rate": 8.586061417605668e-07, "loss": 0.0682, "step": 334 }, { "epoch": 1.6262135922330097, "grad_norm": 2.4383269885779573, "learning_rate": 8.373640606414097e-07, "loss": 0.0559, "step": 335 }, { "epoch": 1.6310679611650487, "grad_norm": 3.386771393269001, "learning_rate": 8.163640108807897e-07, "loss": 1.6835, "step": 336 }, { "epoch": 1.6359223300970873, "grad_norm": 2.4964755511358048, "learning_rate": 7.956072135008336e-07, "loss": 0.0574, "step": 337 }, { "epoch": 1.6407766990291264, "grad_norm": 2.804221131450833, "learning_rate": 7.750948753800508e-07, "loss": 1.6776, "step": 338 }, { "epoch": 1.645631067961165, "grad_norm": 3.05585343475137, "learning_rate": 7.548281891831715e-07, "loss": 0.0599, "step": 339 }, { "epoch": 1.650485436893204, "grad_norm": 3.094692901438052, "learning_rate": 7.348083332917927e-07, "loss": 0.0867, "step": 340 }, { "epoch": 1.6553398058252426, "grad_norm": 5.994214379340551, "learning_rate": 7.150364717358699e-07, "loss": 0.1163, "step": 341 }, { "epoch": 1.6601941747572817, "grad_norm": 2.6685684099421154, "learning_rate": 6.955137541260287e-07, "loss": 0.0729, "step": 342 }, { "epoch": 1.6650485436893203, "grad_norm": 2.614974887848457, "learning_rate": 6.762413155867276e-07, "loss": 0.0669, "step": 343 }, { "epoch": 1.6699029126213594, "grad_norm": 3.7605402445833884, "learning_rate": 6.572202766902569e-07, "loss": 0.102, "step": 344 }, { "epoch": 1.674757281553398, "grad_norm": 2.530314273521925, "learning_rate": 6.384517433915794e-07, "loss": 0.0774, "step": 345 }, { "epoch": 1.679611650485437, "grad_norm": 2.641884474987027, "learning_rate": 6.199368069640343e-07, "loss": 0.0674, "step": 346 }, { "epoch": 1.6844660194174756, "grad_norm": 2.9272910498975544, "learning_rate": 6.016765439358774e-07, "loss": 0.1105, "step": 347 }, { "epoch": 1.6893203883495147, "grad_norm": 2.8644898158113383, "learning_rate": 5.836720160276971e-07, "loss": 0.0629, "step": 348 }, { "epoch": 1.6941747572815533, "grad_norm": 3.2193627421640496, "learning_rate": 5.659242700906719e-07, "loss": 0.0936, "step": 349 }, { "epoch": 1.6990291262135924, "grad_norm": 2.6937432360871156, "learning_rate": 5.484343380457124e-07, "loss": 0.0835, "step": 350 }, { "epoch": 1.703883495145631, "grad_norm": 2.403791791257734, "learning_rate": 5.312032368234527e-07, "loss": 0.0619, "step": 351 }, { "epoch": 1.70873786407767, "grad_norm": 2.8985412438591696, "learning_rate": 5.1423196830513e-07, "loss": 0.0688, "step": 352 }, { "epoch": 1.7135922330097086, "grad_norm": 2.3651095920680394, "learning_rate": 4.975215192643246e-07, "loss": 0.0595, "step": 353 }, { "epoch": 1.7184466019417477, "grad_norm": 2.5298627296726153, "learning_rate": 4.81072861309591e-07, "loss": 2.1163, "step": 354 }, { "epoch": 1.7233009708737863, "grad_norm": 3.119126853868973, "learning_rate": 4.648869508279613e-07, "loss": 0.0736, "step": 355 }, { "epoch": 1.7281553398058254, "grad_norm": 2.695693195432077, "learning_rate": 4.4896472892933693e-07, "loss": 0.0651, "step": 356 }, { "epoch": 1.733009708737864, "grad_norm": 2.324789330239615, "learning_rate": 4.333071213917722e-07, "loss": 0.0571, "step": 357 }, { "epoch": 1.737864077669903, "grad_norm": 2.4268053939586176, "learning_rate": 4.179150386076425e-07, "loss": 1.55, "step": 358 }, { "epoch": 1.7427184466019416, "grad_norm": 3.318783032596993, "learning_rate": 4.027893755307144e-07, "loss": 0.0879, "step": 359 }, { "epoch": 1.7475728155339807, "grad_norm": 3.228808836385332, "learning_rate": 3.8793101162410417e-07, "loss": 0.0806, "step": 360 }, { "epoch": 1.7524271844660193, "grad_norm": 2.5077231830691096, "learning_rate": 3.733408108091485e-07, "loss": 0.0592, "step": 361 }, { "epoch": 1.7572815533980584, "grad_norm": 3.8907140756818803, "learning_rate": 3.5901962141516975e-07, "loss": 0.0906, "step": 362 }, { "epoch": 1.762135922330097, "grad_norm": 3.188616645281919, "learning_rate": 3.4496827613015206e-07, "loss": 0.0893, "step": 363 }, { "epoch": 1.766990291262136, "grad_norm": 4.00676524274261, "learning_rate": 3.3118759195232273e-07, "loss": 0.1123, "step": 364 }, { "epoch": 1.7718446601941746, "grad_norm": 2.82176742226637, "learning_rate": 3.176783701426528e-07, "loss": 0.0783, "step": 365 }, { "epoch": 1.7766990291262137, "grad_norm": 3.035783084499938, "learning_rate": 3.0444139617826605e-07, "loss": 0.0801, "step": 366 }, { "epoch": 1.7815533980582523, "grad_norm": 2.68206770681917, "learning_rate": 2.91477439706771e-07, "loss": 0.0778, "step": 367 }, { "epoch": 1.7864077669902914, "grad_norm": 2.6094497830306818, "learning_rate": 2.787872545015069e-07, "loss": 0.0703, "step": 368 }, { "epoch": 1.79126213592233, "grad_norm": 2.6985662603724836, "learning_rate": 2.663715784177201e-07, "loss": 0.0713, "step": 369 }, { "epoch": 1.796116504854369, "grad_norm": 3.416820336867604, "learning_rate": 2.542311333496622e-07, "loss": 0.0927, "step": 370 }, { "epoch": 1.8009708737864076, "grad_norm": 2.967268889240781, "learning_rate": 2.423666251886114e-07, "loss": 0.0803, "step": 371 }, { "epoch": 1.8058252427184467, "grad_norm": 2.808385614520899, "learning_rate": 2.307787437818365e-07, "loss": 0.0549, "step": 372 }, { "epoch": 1.8106796116504853, "grad_norm": 3.204050738102251, "learning_rate": 2.1946816289248163e-07, "loss": 0.0768, "step": 373 }, { "epoch": 1.8155339805825244, "grad_norm": 2.8887165325007063, "learning_rate": 2.0843554016039326e-07, "loss": 0.0812, "step": 374 }, { "epoch": 1.820388349514563, "grad_norm": 2.4786338107907677, "learning_rate": 1.9768151706388016e-07, "loss": 0.0693, "step": 375 }, { "epoch": 1.825242718446602, "grad_norm": 2.8499069296362567, "learning_rate": 1.8720671888242058e-07, "loss": 0.0698, "step": 376 }, { "epoch": 1.8300970873786406, "grad_norm": 2.986846518621566, "learning_rate": 1.7701175466029895e-07, "loss": 0.073, "step": 377 }, { "epoch": 1.8349514563106797, "grad_norm": 2.9569805825011954, "learning_rate": 1.6709721717120042e-07, "loss": 0.1111, "step": 378 }, { "epoch": 1.8398058252427183, "grad_norm": 2.2641670429414633, "learning_rate": 1.574636828837395e-07, "loss": 0.081, "step": 379 }, { "epoch": 1.8446601941747574, "grad_norm": 2.5283674709842168, "learning_rate": 1.4811171192794628e-07, "loss": 0.0684, "step": 380 }, { "epoch": 1.849514563106796, "grad_norm": 2.897263302225223, "learning_rate": 1.3904184806269705e-07, "loss": 0.0841, "step": 381 }, { "epoch": 1.854368932038835, "grad_norm": 2.354156493900917, "learning_rate": 1.3025461864409395e-07, "loss": 0.0527, "step": 382 }, { "epoch": 1.8592233009708736, "grad_norm": 3.1425590941343917, "learning_rate": 1.2175053459481e-07, "loss": 0.0839, "step": 383 }, { "epoch": 1.8640776699029127, "grad_norm": 2.8771004475766486, "learning_rate": 1.1353009037437523e-07, "loss": 0.0641, "step": 384 }, { "epoch": 1.8689320388349513, "grad_norm": 3.7753913065176854, "learning_rate": 1.0559376395043285e-07, "loss": 0.0945, "step": 385 }, { "epoch": 1.8737864077669903, "grad_norm": 3.045290352139969, "learning_rate": 9.794201677094162e-08, "loss": 0.0691, "step": 386 }, { "epoch": 1.8786407766990292, "grad_norm": 2.827523364996351, "learning_rate": 9.05752937373533e-08, "loss": 0.067, "step": 387 }, { "epoch": 1.883495145631068, "grad_norm": 2.3369063097065697, "learning_rate": 8.34940231787379e-08, "loss": 0.056, "step": 388 }, { "epoch": 1.8883495145631068, "grad_norm": 2.7538101838954683, "learning_rate": 7.66986168268824e-08, "loss": 0.0538, "step": 389 }, { "epoch": 1.8932038834951457, "grad_norm": 2.852941272376346, "learning_rate": 7.018946979234997e-08, "loss": 0.0713, "step": 390 }, { "epoch": 1.8980582524271845, "grad_norm": 2.4418246951319422, "learning_rate": 6.396696054150719e-08, "loss": 0.0555, "step": 391 }, { "epoch": 1.9029126213592233, "grad_norm": 2.9999090182347077, "learning_rate": 5.803145087451945e-08, "loss": 0.0621, "step": 392 }, { "epoch": 1.9077669902912622, "grad_norm": 3.2442934086920667, "learning_rate": 5.238328590431163e-08, "loss": 0.1006, "step": 393 }, { "epoch": 1.912621359223301, "grad_norm": 2.711694124657116, "learning_rate": 4.702279403650534e-08, "loss": 0.0677, "step": 394 }, { "epoch": 1.9174757281553398, "grad_norm": 2.995618798054314, "learning_rate": 4.195028695032133e-08, "loss": 0.0888, "step": 395 }, { "epoch": 1.9223300970873787, "grad_norm": 2.9995330453741804, "learning_rate": 3.716605958046071e-08, "loss": 0.0643, "step": 396 }, { "epoch": 1.9271844660194175, "grad_norm": 3.3748574494740056, "learning_rate": 3.2670390099951985e-08, "loss": 0.07, "step": 397 }, { "epoch": 1.9320388349514563, "grad_norm": 3.7760633589986488, "learning_rate": 2.846353990398065e-08, "loss": 0.0991, "step": 398 }, { "epoch": 1.9368932038834952, "grad_norm": 2.7681700840158876, "learning_rate": 2.4545753594688582e-08, "loss": 1.4371, "step": 399 }, { "epoch": 1.941747572815534, "grad_norm": 3.0753950908772985, "learning_rate": 2.0917258966953735e-08, "loss": 0.083, "step": 400 }, { "epoch": 1.9466019417475728, "grad_norm": 3.136204625362315, "learning_rate": 1.757826699514298e-08, "loss": 0.0755, "step": 401 }, { "epoch": 1.9514563106796117, "grad_norm": 2.6333380164118516, "learning_rate": 1.4528971820846894e-08, "loss": 0.0577, "step": 402 }, { "epoch": 1.9563106796116505, "grad_norm": 2.3026842334958015, "learning_rate": 1.176955074159214e-08, "loss": 0.0553, "step": 403 }, { "epoch": 1.9611650485436893, "grad_norm": 2.8305325809330752, "learning_rate": 9.300164200530815e-09, "loss": 0.0707, "step": 404 }, { "epoch": 1.9660194174757282, "grad_norm": 3.4008450370034047, "learning_rate": 7.120955777112915e-09, "loss": 0.089, "step": 405 }, { "epoch": 1.970873786407767, "grad_norm": 2.862907268733839, "learning_rate": 5.232052178738567e-09, "loss": 0.0642, "step": 406 }, { "epoch": 1.9757281553398058, "grad_norm": 3.6074011718550447, "learning_rate": 3.633563233388926e-09, "loss": 0.0741, "step": 407 }, { "epoch": 1.9805825242718447, "grad_norm": 2.583312048382848, "learning_rate": 2.3255818832423894e-09, "loss": 0.0573, "step": 408 }, { "epoch": 1.9854368932038835, "grad_norm": 2.9051428728952593, "learning_rate": 1.3081841792694783e-09, "loss": 0.0764, "step": 409 }, { "epoch": 1.9902912621359223, "grad_norm": 2.1471755925183484, "learning_rate": 5.814292768108187e-10, "loss": 0.0573, "step": 410 }, { "epoch": 1.9951456310679612, "grad_norm": 2.8556205868247497, "learning_rate": 1.453594321393359e-10, "loss": 0.0679, "step": 411 }, { "epoch": 2.0, "grad_norm": 1.7882390903441006, "learning_rate": 0.0, "loss": 0.0419, "step": 412 }, { "epoch": 2.0, "step": 412, "total_flos": 957358891008.0, "train_loss": 0.20337393274982868, "train_runtime": 258.6726, "train_samples_per_second": 12.688, "train_steps_per_second": 1.593 } ], "logging_steps": 1, "max_steps": 412, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 50000000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 957358891008.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }