{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.961636828644501, "eval_steps": 500, "global_step": 485, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.010230179028132993, "grad_norm": 2.9680692204021657, "learning_rate": 4.0816326530612243e-07, "loss": 1.4918, "step": 1 }, { "epoch": 0.020460358056265986, "grad_norm": 2.9793030995780305, "learning_rate": 8.163265306122449e-07, "loss": 1.4922, "step": 2 }, { "epoch": 0.030690537084398978, "grad_norm": 2.969321218222247, "learning_rate": 1.2244897959183673e-06, "loss": 1.5054, "step": 3 }, { "epoch": 0.04092071611253197, "grad_norm": 2.9555545434896957, "learning_rate": 1.6326530612244897e-06, "loss": 1.4905, "step": 4 }, { "epoch": 0.05115089514066496, "grad_norm": 2.924129624172145, "learning_rate": 2.0408163265306125e-06, "loss": 1.4932, "step": 5 }, { "epoch": 0.061381074168797956, "grad_norm": 2.6580888636085214, "learning_rate": 2.4489795918367347e-06, "loss": 1.4794, "step": 6 }, { "epoch": 0.07161125319693094, "grad_norm": 2.591093932622508, "learning_rate": 2.8571428571428573e-06, "loss": 1.4759, "step": 7 }, { "epoch": 0.08184143222506395, "grad_norm": 2.01581153291475, "learning_rate": 3.2653061224489794e-06, "loss": 1.4735, "step": 8 }, { "epoch": 0.09207161125319693, "grad_norm": 1.9334060390030883, "learning_rate": 3.6734693877551024e-06, "loss": 1.4837, "step": 9 }, { "epoch": 0.10230179028132992, "grad_norm": 1.8504400405167574, "learning_rate": 4.081632653061225e-06, "loss": 1.4699, "step": 10 }, { "epoch": 0.11253196930946291, "grad_norm": 1.8644030222991146, "learning_rate": 4.489795918367348e-06, "loss": 1.4393, "step": 11 }, { "epoch": 0.12276214833759591, "grad_norm": 1.8309189854398389, "learning_rate": 4.897959183673469e-06, "loss": 1.4483, "step": 12 }, { "epoch": 0.1329923273657289, "grad_norm": 1.7173043127138161, "learning_rate": 5.306122448979593e-06, "loss": 1.4257, "step": 13 }, { "epoch": 0.1432225063938619, "grad_norm": 1.4275767362453466, "learning_rate": 5.7142857142857145e-06, "loss": 1.4168, "step": 14 }, { "epoch": 0.1534526854219949, "grad_norm": 1.8639337669180165, "learning_rate": 6.122448979591837e-06, "loss": 1.4141, "step": 15 }, { "epoch": 0.1636828644501279, "grad_norm": 1.8076276760115728, "learning_rate": 6.530612244897959e-06, "loss": 1.4207, "step": 16 }, { "epoch": 0.17391304347826086, "grad_norm": 1.488246921393596, "learning_rate": 6.938775510204082e-06, "loss": 1.3833, "step": 17 }, { "epoch": 0.18414322250639387, "grad_norm": 1.2006642529077214, "learning_rate": 7.346938775510205e-06, "loss": 1.3653, "step": 18 }, { "epoch": 0.19437340153452684, "grad_norm": 0.9870303662837607, "learning_rate": 7.755102040816327e-06, "loss": 1.3624, "step": 19 }, { "epoch": 0.20460358056265984, "grad_norm": 1.0768924276371175, "learning_rate": 8.16326530612245e-06, "loss": 1.3429, "step": 20 }, { "epoch": 0.21483375959079284, "grad_norm": 0.8643447572743981, "learning_rate": 8.571428571428571e-06, "loss": 1.3326, "step": 21 }, { "epoch": 0.22506393861892582, "grad_norm": 0.8388561867151579, "learning_rate": 8.979591836734695e-06, "loss": 1.3552, "step": 22 }, { "epoch": 0.23529411764705882, "grad_norm": 0.7798245298591717, "learning_rate": 9.387755102040818e-06, "loss": 1.3404, "step": 23 }, { "epoch": 0.24552429667519182, "grad_norm": 0.6307322011896973, "learning_rate": 9.795918367346939e-06, "loss": 1.3294, "step": 24 }, { "epoch": 0.2557544757033248, "grad_norm": 0.6211762754003612, "learning_rate": 1.0204081632653063e-05, "loss": 1.3071, "step": 25 }, { "epoch": 0.2659846547314578, "grad_norm": 0.6790720066021528, "learning_rate": 1.0612244897959186e-05, "loss": 1.2991, "step": 26 }, { "epoch": 0.27621483375959077, "grad_norm": 0.5733641641570559, "learning_rate": 1.1020408163265306e-05, "loss": 1.2844, "step": 27 }, { "epoch": 0.2864450127877238, "grad_norm": 0.46457563805110264, "learning_rate": 1.1428571428571429e-05, "loss": 1.3016, "step": 28 }, { "epoch": 0.2966751918158568, "grad_norm": 0.5227342469430273, "learning_rate": 1.1836734693877552e-05, "loss": 1.2793, "step": 29 }, { "epoch": 0.3069053708439898, "grad_norm": 0.5273327366529126, "learning_rate": 1.2244897959183674e-05, "loss": 1.2955, "step": 30 }, { "epoch": 0.3171355498721228, "grad_norm": 0.45083505383897166, "learning_rate": 1.2653061224489798e-05, "loss": 1.2771, "step": 31 }, { "epoch": 0.3273657289002558, "grad_norm": 0.4350323433884286, "learning_rate": 1.3061224489795918e-05, "loss": 1.267, "step": 32 }, { "epoch": 0.3375959079283887, "grad_norm": 0.42399451158557233, "learning_rate": 1.3469387755102042e-05, "loss": 1.2794, "step": 33 }, { "epoch": 0.34782608695652173, "grad_norm": 0.4031684806038015, "learning_rate": 1.3877551020408165e-05, "loss": 1.2789, "step": 34 }, { "epoch": 0.35805626598465473, "grad_norm": 0.35916704531263227, "learning_rate": 1.4285714285714287e-05, "loss": 1.2708, "step": 35 }, { "epoch": 0.36828644501278773, "grad_norm": 0.32004498563079053, "learning_rate": 1.469387755102041e-05, "loss": 1.2545, "step": 36 }, { "epoch": 0.37851662404092073, "grad_norm": 0.33552723666108236, "learning_rate": 1.510204081632653e-05, "loss": 1.2639, "step": 37 }, { "epoch": 0.3887468030690537, "grad_norm": 0.34094700670432593, "learning_rate": 1.5510204081632655e-05, "loss": 1.2453, "step": 38 }, { "epoch": 0.3989769820971867, "grad_norm": 0.2893794341389895, "learning_rate": 1.5918367346938776e-05, "loss": 1.2522, "step": 39 }, { "epoch": 0.4092071611253197, "grad_norm": 0.27610012682474794, "learning_rate": 1.63265306122449e-05, "loss": 1.2503, "step": 40 }, { "epoch": 0.4194373401534527, "grad_norm": 0.2881827494564143, "learning_rate": 1.673469387755102e-05, "loss": 1.2353, "step": 41 }, { "epoch": 0.4296675191815857, "grad_norm": 0.2565696500975483, "learning_rate": 1.7142857142857142e-05, "loss": 1.2351, "step": 42 }, { "epoch": 0.4398976982097187, "grad_norm": 0.24074069177000396, "learning_rate": 1.7551020408163266e-05, "loss": 1.2338, "step": 43 }, { "epoch": 0.45012787723785164, "grad_norm": 0.23515100274411482, "learning_rate": 1.795918367346939e-05, "loss": 1.2526, "step": 44 }, { "epoch": 0.46035805626598464, "grad_norm": 0.23503226195959384, "learning_rate": 1.836734693877551e-05, "loss": 1.2272, "step": 45 }, { "epoch": 0.47058823529411764, "grad_norm": 0.230214509612993, "learning_rate": 1.8775510204081636e-05, "loss": 1.2383, "step": 46 }, { "epoch": 0.48081841432225064, "grad_norm": 0.20032859057078034, "learning_rate": 1.9183673469387756e-05, "loss": 1.2349, "step": 47 }, { "epoch": 0.49104859335038364, "grad_norm": 0.22576692623941616, "learning_rate": 1.9591836734693877e-05, "loss": 1.2113, "step": 48 }, { "epoch": 0.5012787723785166, "grad_norm": 0.1946251636688442, "learning_rate": 2e-05, "loss": 1.2142, "step": 49 }, { "epoch": 0.5115089514066496, "grad_norm": 0.19632060790517664, "learning_rate": 1.9999740405855478e-05, "loss": 1.2176, "step": 50 }, { "epoch": 0.5217391304347826, "grad_norm": 0.19447569911738155, "learning_rate": 1.9998961636899736e-05, "loss": 1.2023, "step": 51 }, { "epoch": 0.5319693094629157, "grad_norm": 0.20076523236079202, "learning_rate": 1.9997663733565537e-05, "loss": 1.2132, "step": 52 }, { "epoch": 0.5421994884910486, "grad_norm": 0.16158305629528763, "learning_rate": 1.9995846763238514e-05, "loss": 1.1962, "step": 53 }, { "epoch": 0.5524296675191815, "grad_norm": 0.18018620164266, "learning_rate": 1.999351082025363e-05, "loss": 1.1976, "step": 54 }, { "epoch": 0.5626598465473146, "grad_norm": 0.15154379624162267, "learning_rate": 1.9990656025890315e-05, "loss": 1.191, "step": 55 }, { "epoch": 0.5728900255754475, "grad_norm": 0.15980510282118704, "learning_rate": 1.9987282528366147e-05, "loss": 1.1897, "step": 56 }, { "epoch": 0.5831202046035806, "grad_norm": 0.15778849273738765, "learning_rate": 1.9983390502829168e-05, "loss": 1.1934, "step": 57 }, { "epoch": 0.5933503836317136, "grad_norm": 0.16461050838548058, "learning_rate": 1.997898015134878e-05, "loss": 1.1978, "step": 58 }, { "epoch": 0.6035805626598465, "grad_norm": 0.1418094646316852, "learning_rate": 1.997405170290528e-05, "loss": 1.1782, "step": 59 }, { "epoch": 0.6138107416879796, "grad_norm": 0.16306093980956446, "learning_rate": 1.9968605413377924e-05, "loss": 1.1826, "step": 60 }, { "epoch": 0.6240409207161125, "grad_norm": 0.13952029942215738, "learning_rate": 1.9962641565531694e-05, "loss": 1.1989, "step": 61 }, { "epoch": 0.6342710997442456, "grad_norm": 0.14705068118772557, "learning_rate": 1.9956160469002584e-05, "loss": 1.2026, "step": 62 }, { "epoch": 0.6445012787723785, "grad_norm": 0.14464630824632058, "learning_rate": 1.994916246028154e-05, "loss": 1.2003, "step": 63 }, { "epoch": 0.6547314578005116, "grad_norm": 0.15061394669737563, "learning_rate": 1.9941647902696975e-05, "loss": 1.195, "step": 64 }, { "epoch": 0.6649616368286445, "grad_norm": 0.16098188414319, "learning_rate": 1.9933617186395917e-05, "loss": 1.194, "step": 65 }, { "epoch": 0.6751918158567775, "grad_norm": 0.14949117445630275, "learning_rate": 1.9925070728323758e-05, "loss": 1.1832, "step": 66 }, { "epoch": 0.6854219948849105, "grad_norm": 0.15495432084624133, "learning_rate": 1.9916008972202586e-05, "loss": 1.1847, "step": 67 }, { "epoch": 0.6956521739130435, "grad_norm": 0.14747263262221286, "learning_rate": 1.9906432388508176e-05, "loss": 1.1827, "step": 68 }, { "epoch": 0.7058823529411765, "grad_norm": 0.12642367461003082, "learning_rate": 1.9896341474445526e-05, "loss": 1.1842, "step": 69 }, { "epoch": 0.7161125319693095, "grad_norm": 0.12197521914147792, "learning_rate": 1.9885736753923084e-05, "loss": 1.1911, "step": 70 }, { "epoch": 0.7263427109974424, "grad_norm": 0.13487767100731402, "learning_rate": 1.987461877752552e-05, "loss": 1.1669, "step": 71 }, { "epoch": 0.7365728900255755, "grad_norm": 0.1525911065503744, "learning_rate": 1.9862988122485145e-05, "loss": 1.1762, "step": 72 }, { "epoch": 0.7468030690537084, "grad_norm": 0.12279851649377206, "learning_rate": 1.985084539265195e-05, "loss": 1.1761, "step": 73 }, { "epoch": 0.7570332480818415, "grad_norm": 0.1298972144168733, "learning_rate": 1.983819121846225e-05, "loss": 1.1654, "step": 74 }, { "epoch": 0.7672634271099744, "grad_norm": 0.14042259603327337, "learning_rate": 1.982502625690595e-05, "loss": 1.1841, "step": 75 }, { "epoch": 0.7774936061381074, "grad_norm": 0.11120933213565785, "learning_rate": 1.981135119149243e-05, "loss": 1.1734, "step": 76 }, { "epoch": 0.7877237851662404, "grad_norm": 0.13324071865424547, "learning_rate": 1.9797166732215078e-05, "loss": 1.1613, "step": 77 }, { "epoch": 0.7979539641943734, "grad_norm": 0.1286032289808526, "learning_rate": 1.9782473615514403e-05, "loss": 1.1795, "step": 78 }, { "epoch": 0.8081841432225064, "grad_norm": 0.11823385018853347, "learning_rate": 1.9767272604239823e-05, "loss": 1.1622, "step": 79 }, { "epoch": 0.8184143222506394, "grad_norm": 0.13046952515592894, "learning_rate": 1.9751564487610038e-05, "loss": 1.167, "step": 80 }, { "epoch": 0.8286445012787724, "grad_norm": 0.11680151126070633, "learning_rate": 1.973535008117207e-05, "loss": 1.1744, "step": 81 }, { "epoch": 0.8388746803069054, "grad_norm": 0.11663740741574687, "learning_rate": 1.971863022675891e-05, "loss": 1.173, "step": 82 }, { "epoch": 0.8491048593350383, "grad_norm": 0.14661876324953774, "learning_rate": 1.9701405792445815e-05, "loss": 1.1761, "step": 83 }, { "epoch": 0.8593350383631714, "grad_norm": 0.12250709236001564, "learning_rate": 1.9683677672505254e-05, "loss": 1.1576, "step": 84 }, { "epoch": 0.8695652173913043, "grad_norm": 0.11585902164807296, "learning_rate": 1.9665446787360444e-05, "loss": 1.1739, "step": 85 }, { "epoch": 0.8797953964194374, "grad_norm": 0.15581304410470315, "learning_rate": 1.9646714083537596e-05, "loss": 1.1638, "step": 86 }, { "epoch": 0.8900255754475703, "grad_norm": 0.12603886734487554, "learning_rate": 1.962748053361675e-05, "loss": 1.164, "step": 87 }, { "epoch": 0.9002557544757033, "grad_norm": 0.13178331243449873, "learning_rate": 1.96077471361813e-05, "loss": 1.1645, "step": 88 }, { "epoch": 0.9104859335038363, "grad_norm": 0.11137164415189152, "learning_rate": 1.9587514915766124e-05, "loss": 1.157, "step": 89 }, { "epoch": 0.9207161125319693, "grad_norm": 0.13892513490000424, "learning_rate": 1.9566784922804415e-05, "loss": 1.1651, "step": 90 }, { "epoch": 0.9309462915601023, "grad_norm": 0.1218054692399559, "learning_rate": 1.9545558233573136e-05, "loss": 1.1559, "step": 91 }, { "epoch": 0.9411764705882353, "grad_norm": 0.13697640794360152, "learning_rate": 1.9523835950137128e-05, "loss": 1.177, "step": 92 }, { "epoch": 0.9514066496163683, "grad_norm": 0.1744034784164467, "learning_rate": 1.950161920029191e-05, "loss": 1.1674, "step": 93 }, { "epoch": 0.9616368286445013, "grad_norm": 0.178654071814111, "learning_rate": 1.947890913750511e-05, "loss": 1.1671, "step": 94 }, { "epoch": 0.9718670076726342, "grad_norm": 0.2472414416035624, "learning_rate": 1.9455706940856602e-05, "loss": 1.1574, "step": 95 }, { "epoch": 0.9820971867007673, "grad_norm": 0.2765062915428777, "learning_rate": 1.9432013814977258e-05, "loss": 1.1546, "step": 96 }, { "epoch": 0.9923273657289002, "grad_norm": 0.3175697283209886, "learning_rate": 1.940783098998643e-05, "loss": 1.1797, "step": 97 }, { "epoch": 1.0025575447570332, "grad_norm": 0.40604980276436853, "learning_rate": 1.9383159721428067e-05, "loss": 1.4586, "step": 98 }, { "epoch": 1.0127877237851663, "grad_norm": 0.5937576264262995, "learning_rate": 1.9358001290205542e-05, "loss": 1.1488, "step": 99 }, { "epoch": 1.0230179028132993, "grad_norm": 0.662267597507883, "learning_rate": 1.9332357002515146e-05, "loss": 1.1753, "step": 100 }, { "epoch": 1.0332480818414322, "grad_norm": 0.36133591446688756, "learning_rate": 1.9306228189778255e-05, "loss": 1.1567, "step": 101 }, { "epoch": 1.0434782608695652, "grad_norm": 0.5023370193239342, "learning_rate": 1.9279616208572236e-05, "loss": 1.159, "step": 102 }, { "epoch": 1.0537084398976981, "grad_norm": 0.602073145263804, "learning_rate": 1.925252244055998e-05, "loss": 1.1328, "step": 103 }, { "epoch": 1.0639386189258313, "grad_norm": 0.4335005423646633, "learning_rate": 1.9224948292418194e-05, "loss": 1.1677, "step": 104 }, { "epoch": 1.0741687979539642, "grad_norm": 0.6348816968118507, "learning_rate": 1.9196895195764363e-05, "loss": 1.151, "step": 105 }, { "epoch": 1.0843989769820972, "grad_norm": 0.4340476599018384, "learning_rate": 1.916836460708241e-05, "loss": 1.1466, "step": 106 }, { "epoch": 1.0946291560102301, "grad_norm": 0.4453871606686273, "learning_rate": 1.9139358007647085e-05, "loss": 1.1369, "step": 107 }, { "epoch": 1.104859335038363, "grad_norm": 0.4370521880410465, "learning_rate": 1.9109876903447065e-05, "loss": 1.1709, "step": 108 }, { "epoch": 1.1150895140664963, "grad_norm": 0.27359538771014974, "learning_rate": 1.907992282510675e-05, "loss": 1.1472, "step": 109 }, { "epoch": 1.1253196930946292, "grad_norm": 0.4315498825592958, "learning_rate": 1.9049497327806815e-05, "loss": 1.1366, "step": 110 }, { "epoch": 1.1355498721227621, "grad_norm": 0.25555898671819416, "learning_rate": 1.901860199120344e-05, "loss": 1.1439, "step": 111 }, { "epoch": 1.145780051150895, "grad_norm": 0.36085310229175666, "learning_rate": 1.8987238419346328e-05, "loss": 1.131, "step": 112 }, { "epoch": 1.156010230179028, "grad_norm": 0.32586153213667385, "learning_rate": 1.8955408240595396e-05, "loss": 1.1528, "step": 113 }, { "epoch": 1.1662404092071612, "grad_norm": 0.2559147263924166, "learning_rate": 1.8923113107536248e-05, "loss": 1.1402, "step": 114 }, { "epoch": 1.1764705882352942, "grad_norm": 0.2572466837792148, "learning_rate": 1.8890354696894374e-05, "loss": 1.1374, "step": 115 }, { "epoch": 1.186700767263427, "grad_norm": 0.2569505931640539, "learning_rate": 1.8857134709448094e-05, "loss": 1.1525, "step": 116 }, { "epoch": 1.19693094629156, "grad_norm": 0.24516109262934607, "learning_rate": 1.8823454869940243e-05, "loss": 1.1516, "step": 117 }, { "epoch": 1.207161125319693, "grad_norm": 0.23389605377245185, "learning_rate": 1.8789316926988656e-05, "loss": 1.1325, "step": 118 }, { "epoch": 1.2173913043478262, "grad_norm": 0.2514129866724698, "learning_rate": 1.8754722652995346e-05, "loss": 1.1367, "step": 119 }, { "epoch": 1.227621483375959, "grad_norm": 0.19859095959433043, "learning_rate": 1.871967384405451e-05, "loss": 1.1573, "step": 120 }, { "epoch": 1.237851662404092, "grad_norm": 0.22448306655154832, "learning_rate": 1.8684172319859258e-05, "loss": 1.1474, "step": 121 }, { "epoch": 1.248081841432225, "grad_norm": 0.1979089184838938, "learning_rate": 1.8648219923607156e-05, "loss": 1.1417, "step": 122 }, { "epoch": 1.258312020460358, "grad_norm": 0.21775668088089206, "learning_rate": 1.861181852190451e-05, "loss": 1.1527, "step": 123 }, { "epoch": 1.2685421994884911, "grad_norm": 0.1693324499283649, "learning_rate": 1.8574970004669464e-05, "loss": 1.1437, "step": 124 }, { "epoch": 1.278772378516624, "grad_norm": 0.19440366039529086, "learning_rate": 1.8537676285033886e-05, "loss": 1.1268, "step": 125 }, { "epoch": 1.289002557544757, "grad_norm": 0.19012227208411686, "learning_rate": 1.8499939299244027e-05, "loss": 1.1414, "step": 126 }, { "epoch": 1.29923273657289, "grad_norm": 0.15040484626222902, "learning_rate": 1.8461761006559982e-05, "loss": 1.1387, "step": 127 }, { "epoch": 1.309462915601023, "grad_norm": 0.21285846844492884, "learning_rate": 1.842314338915401e-05, "loss": 1.1441, "step": 128 }, { "epoch": 1.319693094629156, "grad_norm": 0.16942598357957434, "learning_rate": 1.838408845200758e-05, "loss": 1.121, "step": 129 }, { "epoch": 1.329923273657289, "grad_norm": 0.1838939187726863, "learning_rate": 1.8344598222807285e-05, "loss": 1.1441, "step": 130 }, { "epoch": 1.340153452685422, "grad_norm": 0.19966825773374916, "learning_rate": 1.8304674751839583e-05, "loss": 1.1518, "step": 131 }, { "epoch": 1.350383631713555, "grad_norm": 0.1836599174381594, "learning_rate": 1.826432011188433e-05, "loss": 1.1523, "step": 132 }, { "epoch": 1.3606138107416879, "grad_norm": 0.15715513254147773, "learning_rate": 1.8223536398107177e-05, "loss": 1.1214, "step": 133 }, { "epoch": 1.370843989769821, "grad_norm": 0.1660889794226329, "learning_rate": 1.818232572795078e-05, "loss": 1.1624, "step": 134 }, { "epoch": 1.381074168797954, "grad_norm": 0.17902123799574446, "learning_rate": 1.8140690241024872e-05, "loss": 1.1379, "step": 135 }, { "epoch": 1.391304347826087, "grad_norm": 0.13596272277116248, "learning_rate": 1.8098632098995174e-05, "loss": 1.1428, "step": 136 }, { "epoch": 1.40153452685422, "grad_norm": 0.15001095934645328, "learning_rate": 1.8056153485471167e-05, "loss": 1.1306, "step": 137 }, { "epoch": 1.4117647058823528, "grad_norm": 0.16523905732617533, "learning_rate": 1.801325660589272e-05, "loss": 1.1375, "step": 138 }, { "epoch": 1.421994884910486, "grad_norm": 0.14650744790077894, "learning_rate": 1.7969943687415575e-05, "loss": 1.137, "step": 139 }, { "epoch": 1.432225063938619, "grad_norm": 0.13193408487358604, "learning_rate": 1.792621697879575e-05, "loss": 1.1292, "step": 140 }, { "epoch": 1.4424552429667519, "grad_norm": 0.16949625864140141, "learning_rate": 1.788207875027274e-05, "loss": 1.1436, "step": 141 }, { "epoch": 1.452685421994885, "grad_norm": 0.13611829442543721, "learning_rate": 1.783753129345169e-05, "loss": 1.1323, "step": 142 }, { "epoch": 1.4629156010230178, "grad_norm": 0.13610276012105194, "learning_rate": 1.7792576921184374e-05, "loss": 1.1343, "step": 143 }, { "epoch": 1.473145780051151, "grad_norm": 0.15095390435543926, "learning_rate": 1.774721796744916e-05, "loss": 1.1445, "step": 144 }, { "epoch": 1.4833759590792839, "grad_norm": 0.1273246788166071, "learning_rate": 1.7701456787229805e-05, "loss": 1.136, "step": 145 }, { "epoch": 1.4936061381074168, "grad_norm": 0.14116173015502784, "learning_rate": 1.76552957563932e-05, "loss": 1.1454, "step": 146 }, { "epoch": 1.50383631713555, "grad_norm": 0.11455718670702662, "learning_rate": 1.7608737271566004e-05, "loss": 1.1314, "step": 147 }, { "epoch": 1.5140664961636827, "grad_norm": 0.11707583340336068, "learning_rate": 1.756178375001023e-05, "loss": 1.1225, "step": 148 }, { "epoch": 1.5242966751918159, "grad_norm": 0.12813321712087092, "learning_rate": 1.751443762949772e-05, "loss": 1.1166, "step": 149 }, { "epoch": 1.5345268542199488, "grad_norm": 0.09614543623160586, "learning_rate": 1.7466701368183612e-05, "loss": 1.1548, "step": 150 }, { "epoch": 1.5447570332480818, "grad_norm": 0.13555538486652807, "learning_rate": 1.741857744447869e-05, "loss": 1.1226, "step": 151 }, { "epoch": 1.554987212276215, "grad_norm": 0.11964836825975711, "learning_rate": 1.7370068356920708e-05, "loss": 1.1237, "step": 152 }, { "epoch": 1.5652173913043477, "grad_norm": 0.14011323681622234, "learning_rate": 1.732117662404469e-05, "loss": 1.1259, "step": 153 }, { "epoch": 1.5754475703324808, "grad_norm": 0.125097689670342, "learning_rate": 1.7271904784252143e-05, "loss": 1.1384, "step": 154 }, { "epoch": 1.5856777493606138, "grad_norm": 0.12567403280510567, "learning_rate": 1.7222255395679298e-05, "loss": 1.1113, "step": 155 }, { "epoch": 1.5959079283887467, "grad_norm": 0.11005916710940143, "learning_rate": 1.7172231036064257e-05, "loss": 1.1523, "step": 156 }, { "epoch": 1.60613810741688, "grad_norm": 0.10054450277852764, "learning_rate": 1.712183430261319e-05, "loss": 1.1384, "step": 157 }, { "epoch": 1.6163682864450126, "grad_norm": 0.11256739657205644, "learning_rate": 1.7071067811865477e-05, "loss": 1.1185, "step": 158 }, { "epoch": 1.6265984654731458, "grad_norm": 0.11172469109501333, "learning_rate": 1.7019934199557868e-05, "loss": 1.132, "step": 159 }, { "epoch": 1.6368286445012787, "grad_norm": 0.11419941988437013, "learning_rate": 1.696843612048763e-05, "loss": 1.135, "step": 160 }, { "epoch": 1.6470588235294117, "grad_norm": 0.12187411865079387, "learning_rate": 1.691657624837472e-05, "loss": 1.1357, "step": 161 }, { "epoch": 1.6572890025575449, "grad_norm": 0.1262071005249972, "learning_rate": 1.6864357275722966e-05, "loss": 1.1139, "step": 162 }, { "epoch": 1.6675191815856778, "grad_norm": 0.1377567391203018, "learning_rate": 1.6811781913680273e-05, "loss": 1.1367, "step": 163 }, { "epoch": 1.6777493606138107, "grad_norm": 0.1265242326310899, "learning_rate": 1.6758852891897865e-05, "loss": 1.1324, "step": 164 }, { "epoch": 1.6879795396419437, "grad_norm": 0.14516739070283927, "learning_rate": 1.6705572958388576e-05, "loss": 1.1391, "step": 165 }, { "epoch": 1.6982097186700766, "grad_norm": 0.15388764486149203, "learning_rate": 1.665194487938415e-05, "loss": 1.1358, "step": 166 }, { "epoch": 1.7084398976982098, "grad_norm": 0.12218006800143733, "learning_rate": 1.659797143919165e-05, "loss": 1.1285, "step": 167 }, { "epoch": 1.7186700767263428, "grad_norm": 0.11814518100898261, "learning_rate": 1.654365544004888e-05, "loss": 1.1293, "step": 168 }, { "epoch": 1.7289002557544757, "grad_norm": 0.12495491786958067, "learning_rate": 1.6488999701978905e-05, "loss": 1.1383, "step": 169 }, { "epoch": 1.7391304347826086, "grad_norm": 0.11312201922979076, "learning_rate": 1.643400706264364e-05, "loss": 1.122, "step": 170 }, { "epoch": 1.7493606138107416, "grad_norm": 0.13047799765384857, "learning_rate": 1.6378680377196526e-05, "loss": 1.1327, "step": 171 }, { "epoch": 1.7595907928388748, "grad_norm": 0.12220386542272418, "learning_rate": 1.6323022518134265e-05, "loss": 1.1411, "step": 172 }, { "epoch": 1.7698209718670077, "grad_norm": 0.11614421703299331, "learning_rate": 1.6267036375147728e-05, "loss": 1.1239, "step": 173 }, { "epoch": 1.7800511508951407, "grad_norm": 0.12400012913504478, "learning_rate": 1.6210724854971885e-05, "loss": 1.1257, "step": 174 }, { "epoch": 1.7902813299232738, "grad_norm": 0.11320054102738449, "learning_rate": 1.615409088123493e-05, "loss": 1.127, "step": 175 }, { "epoch": 1.8005115089514065, "grad_norm": 0.1099389180653249, "learning_rate": 1.6097137394306444e-05, "loss": 1.1271, "step": 176 }, { "epoch": 1.8107416879795397, "grad_norm": 0.10199483281375364, "learning_rate": 1.6039867351144778e-05, "loss": 1.1108, "step": 177 }, { "epoch": 1.8209718670076727, "grad_norm": 0.10388483890530639, "learning_rate": 1.5982283725143498e-05, "loss": 1.1358, "step": 178 }, { "epoch": 1.8312020460358056, "grad_norm": 0.11601535978727218, "learning_rate": 1.5924389505977038e-05, "loss": 1.1166, "step": 179 }, { "epoch": 1.8414322250639388, "grad_norm": 0.09859508045949249, "learning_rate": 1.5866187699445447e-05, "loss": 1.1229, "step": 180 }, { "epoch": 1.8516624040920715, "grad_norm": 0.1220353385259135, "learning_rate": 1.5807681327318372e-05, "loss": 1.1253, "step": 181 }, { "epoch": 1.8618925831202047, "grad_norm": 0.11708066933398557, "learning_rate": 1.574887342717813e-05, "loss": 1.1128, "step": 182 }, { "epoch": 1.8721227621483376, "grad_norm": 0.1418775072084601, "learning_rate": 1.5689767052262028e-05, "loss": 1.1247, "step": 183 }, { "epoch": 1.8823529411764706, "grad_norm": 0.148586843928829, "learning_rate": 1.5630365271303826e-05, "loss": 1.1306, "step": 184 }, { "epoch": 1.8925831202046037, "grad_norm": 0.1348488555681305, "learning_rate": 1.557067116837444e-05, "loss": 1.1205, "step": 185 }, { "epoch": 1.9028132992327365, "grad_norm": 0.11709173080052522, "learning_rate": 1.5510687842721775e-05, "loss": 1.1133, "step": 186 }, { "epoch": 1.9130434782608696, "grad_norm": 0.1372496646066335, "learning_rate": 1.545041840860986e-05, "loss": 1.1228, "step": 187 }, { "epoch": 1.9232736572890026, "grad_norm": 0.10216894869718217, "learning_rate": 1.538986599515713e-05, "loss": 1.1257, "step": 188 }, { "epoch": 1.9335038363171355, "grad_norm": 0.1268305664534445, "learning_rate": 1.5329033746173975e-05, "loss": 1.1116, "step": 189 }, { "epoch": 1.9437340153452687, "grad_norm": 0.12401333208856333, "learning_rate": 1.526792481999953e-05, "loss": 1.1372, "step": 190 }, { "epoch": 1.9539641943734014, "grad_norm": 0.11278299580097981, "learning_rate": 1.520654238933767e-05, "loss": 1.1349, "step": 191 }, { "epoch": 1.9641943734015346, "grad_norm": 0.11007722683311433, "learning_rate": 1.5144889641092314e-05, "loss": 1.1089, "step": 192 }, { "epoch": 1.9744245524296675, "grad_norm": 0.12445018287210001, "learning_rate": 1.5082969776201948e-05, "loss": 1.1191, "step": 193 }, { "epoch": 1.9846547314578005, "grad_norm": 0.11815257299638503, "learning_rate": 1.5020786009473445e-05, "loss": 1.1262, "step": 194 }, { "epoch": 1.9948849104859336, "grad_norm": 0.10710019216361717, "learning_rate": 1.4958341569415149e-05, "loss": 1.2144, "step": 195 }, { "epoch": 2.0051150895140664, "grad_norm": 0.13680138524042837, "learning_rate": 1.489563969806926e-05, "loss": 1.2976, "step": 196 }, { "epoch": 2.0153452685421995, "grad_norm": 0.13909255340977358, "learning_rate": 1.483268365084351e-05, "loss": 1.1333, "step": 197 }, { "epoch": 2.0255754475703327, "grad_norm": 0.12966130740452902, "learning_rate": 1.4769476696342138e-05, "loss": 1.1145, "step": 198 }, { "epoch": 2.0358056265984654, "grad_norm": 0.13308962694641097, "learning_rate": 1.4706022116196208e-05, "loss": 1.0925, "step": 199 }, { "epoch": 2.0460358056265986, "grad_norm": 0.13836154144614216, "learning_rate": 1.4642323204893202e-05, "loss": 1.1401, "step": 200 }, { "epoch": 2.0562659846547313, "grad_norm": 0.1345421546077571, "learning_rate": 1.4578383269606004e-05, "loss": 1.1084, "step": 201 }, { "epoch": 2.0664961636828645, "grad_norm": 0.13295696501970422, "learning_rate": 1.451420563002117e-05, "loss": 1.1345, "step": 202 }, { "epoch": 2.0767263427109977, "grad_norm": 0.1368189085799244, "learning_rate": 1.4449793618166594e-05, "loss": 1.1093, "step": 203 }, { "epoch": 2.0869565217391304, "grad_norm": 0.12975314983600814, "learning_rate": 1.4385150578238492e-05, "loss": 1.1084, "step": 204 }, { "epoch": 2.0971867007672635, "grad_norm": 0.11804562627200785, "learning_rate": 1.4320279866427798e-05, "loss": 1.1066, "step": 205 }, { "epoch": 2.1074168797953963, "grad_norm": 0.14485605363891624, "learning_rate": 1.42551848507459e-05, "loss": 1.1186, "step": 206 }, { "epoch": 2.1176470588235294, "grad_norm": 0.15539527961244817, "learning_rate": 1.4189868910849779e-05, "loss": 1.1237, "step": 207 }, { "epoch": 2.1278772378516626, "grad_norm": 0.13584185646219504, "learning_rate": 1.412433543786654e-05, "loss": 1.1253, "step": 208 }, { "epoch": 2.1381074168797953, "grad_norm": 0.12759935058536961, "learning_rate": 1.4058587834217356e-05, "loss": 1.1353, "step": 209 }, { "epoch": 2.1483375959079285, "grad_norm": 0.13587867944647591, "learning_rate": 1.3992629513440818e-05, "loss": 1.1106, "step": 210 }, { "epoch": 2.1585677749360612, "grad_norm": 0.14126112287927203, "learning_rate": 1.392646390001569e-05, "loss": 1.1387, "step": 211 }, { "epoch": 2.1687979539641944, "grad_norm": 0.13920905630364525, "learning_rate": 1.3860094429183138e-05, "loss": 1.1072, "step": 212 }, { "epoch": 2.1790281329923276, "grad_norm": 0.14003707117313693, "learning_rate": 1.3793524546768358e-05, "loss": 1.1279, "step": 213 }, { "epoch": 2.1892583120204603, "grad_norm": 0.10708859903081283, "learning_rate": 1.3726757709001693e-05, "loss": 1.102, "step": 214 }, { "epoch": 2.1994884910485935, "grad_norm": 0.16770915884440907, "learning_rate": 1.3659797382339162e-05, "loss": 1.1454, "step": 215 }, { "epoch": 2.209718670076726, "grad_norm": 0.1264707297789573, "learning_rate": 1.3592647043282514e-05, "loss": 1.1222, "step": 216 }, { "epoch": 2.2199488491048593, "grad_norm": 0.14938625973325317, "learning_rate": 1.3525310178198707e-05, "loss": 1.1101, "step": 217 }, { "epoch": 2.2301790281329925, "grad_norm": 0.12743491506936716, "learning_rate": 1.3457790283138928e-05, "loss": 1.1182, "step": 218 }, { "epoch": 2.2404092071611252, "grad_norm": 0.12731712604770273, "learning_rate": 1.3390090863657048e-05, "loss": 1.118, "step": 219 }, { "epoch": 2.2506393861892584, "grad_norm": 0.12996965404030442, "learning_rate": 1.3322215434627647e-05, "loss": 1.0986, "step": 220 }, { "epoch": 2.260869565217391, "grad_norm": 0.1014820010414607, "learning_rate": 1.325416752006351e-05, "loss": 1.1039, "step": 221 }, { "epoch": 2.2710997442455243, "grad_norm": 0.13111053844563744, "learning_rate": 1.3185950652932673e-05, "loss": 1.1082, "step": 222 }, { "epoch": 2.2813299232736575, "grad_norm": 0.11831002399895187, "learning_rate": 1.311756837497499e-05, "loss": 1.1226, "step": 223 }, { "epoch": 2.29156010230179, "grad_norm": 0.137232554220391, "learning_rate": 1.3049024236518244e-05, "loss": 1.1249, "step": 224 }, { "epoch": 2.3017902813299234, "grad_norm": 0.13671397230964077, "learning_rate": 1.2980321796293838e-05, "loss": 1.1075, "step": 225 }, { "epoch": 2.312020460358056, "grad_norm": 0.12494721084839672, "learning_rate": 1.291146462125201e-05, "loss": 1.1029, "step": 226 }, { "epoch": 2.3222506393861893, "grad_norm": 0.14039695859339074, "learning_rate": 1.284245628637665e-05, "loss": 1.1111, "step": 227 }, { "epoch": 2.3324808184143224, "grad_norm": 0.11787251379595731, "learning_rate": 1.2773300374499687e-05, "loss": 1.1081, "step": 228 }, { "epoch": 2.342710997442455, "grad_norm": 0.1584133827138455, "learning_rate": 1.2704000476115079e-05, "loss": 1.1278, "step": 229 }, { "epoch": 2.3529411764705883, "grad_norm": 0.13106007506392522, "learning_rate": 1.2634560189192395e-05, "loss": 1.0909, "step": 230 }, { "epoch": 2.363171355498721, "grad_norm": 0.13116311842386333, "learning_rate": 1.256498311899001e-05, "loss": 1.1032, "step": 231 }, { "epoch": 2.373401534526854, "grad_norm": 0.1287142815063066, "learning_rate": 1.2495272877867925e-05, "loss": 1.118, "step": 232 }, { "epoch": 2.3836317135549874, "grad_norm": 0.13403850069897819, "learning_rate": 1.2425433085100224e-05, "loss": 1.1216, "step": 233 }, { "epoch": 2.39386189258312, "grad_norm": 0.1262977190265194, "learning_rate": 1.2355467366687156e-05, "loss": 1.0937, "step": 234 }, { "epoch": 2.4040920716112533, "grad_norm": 0.14937165664493968, "learning_rate": 1.2285379355166893e-05, "loss": 1.1203, "step": 235 }, { "epoch": 2.414322250639386, "grad_norm": 0.10443028741682583, "learning_rate": 1.2215172689426902e-05, "loss": 1.1026, "step": 236 }, { "epoch": 2.424552429667519, "grad_norm": 0.13445371377807008, "learning_rate": 1.2144851014515055e-05, "loss": 1.1001, "step": 237 }, { "epoch": 2.4347826086956523, "grad_norm": 0.11573910445022909, "learning_rate": 1.2074417981450361e-05, "loss": 1.1005, "step": 238 }, { "epoch": 2.445012787723785, "grad_norm": 0.11671176905645508, "learning_rate": 1.2003877247033411e-05, "loss": 1.117, "step": 239 }, { "epoch": 2.455242966751918, "grad_norm": 0.1190989314812314, "learning_rate": 1.1933232473656527e-05, "loss": 1.0794, "step": 240 }, { "epoch": 2.4654731457800514, "grad_norm": 0.10679516221645337, "learning_rate": 1.1862487329113606e-05, "loss": 1.1318, "step": 241 }, { "epoch": 2.475703324808184, "grad_norm": 0.13350837148881556, "learning_rate": 1.179164548640971e-05, "loss": 1.1049, "step": 242 }, { "epoch": 2.4859335038363173, "grad_norm": 0.12701203620692855, "learning_rate": 1.172071062357035e-05, "loss": 1.111, "step": 243 }, { "epoch": 2.49616368286445, "grad_norm": 0.11678661469709524, "learning_rate": 1.164968642345053e-05, "loss": 1.099, "step": 244 }, { "epoch": 2.506393861892583, "grad_norm": 0.11990378754888464, "learning_rate": 1.1578576573543541e-05, "loss": 1.1025, "step": 245 }, { "epoch": 2.516624040920716, "grad_norm": 0.10660867730608625, "learning_rate": 1.150738476578952e-05, "loss": 1.0885, "step": 246 }, { "epoch": 2.526854219948849, "grad_norm": 0.11921290086430118, "learning_rate": 1.1436114696383749e-05, "loss": 1.1058, "step": 247 }, { "epoch": 2.5370843989769822, "grad_norm": 0.09384183354908426, "learning_rate": 1.1364770065584771e-05, "loss": 1.1122, "step": 248 }, { "epoch": 2.547314578005115, "grad_norm": 0.11097772926278181, "learning_rate": 1.1293354577522264e-05, "loss": 1.1015, "step": 249 }, { "epoch": 2.557544757033248, "grad_norm": 0.11081074618596387, "learning_rate": 1.1221871940004731e-05, "loss": 1.0971, "step": 250 }, { "epoch": 2.5677749360613813, "grad_norm": 0.10120509811431277, "learning_rate": 1.1150325864327003e-05, "loss": 1.1157, "step": 251 }, { "epoch": 2.578005115089514, "grad_norm": 0.10954496083156834, "learning_rate": 1.1078720065077542e-05, "loss": 1.1165, "step": 252 }, { "epoch": 2.588235294117647, "grad_norm": 0.10280287963419077, "learning_rate": 1.1007058259945584e-05, "loss": 1.105, "step": 253 }, { "epoch": 2.59846547314578, "grad_norm": 0.10403424910186372, "learning_rate": 1.0935344169528132e-05, "loss": 1.1029, "step": 254 }, { "epoch": 2.608695652173913, "grad_norm": 0.1259317513131597, "learning_rate": 1.0863581517136776e-05, "loss": 1.0921, "step": 255 }, { "epoch": 2.618925831202046, "grad_norm": 0.10274820060232957, "learning_rate": 1.0791774028604385e-05, "loss": 1.1069, "step": 256 }, { "epoch": 2.629156010230179, "grad_norm": 0.1240709513973648, "learning_rate": 1.0719925432091671e-05, "loss": 1.1097, "step": 257 }, { "epoch": 2.639386189258312, "grad_norm": 0.10489926653550496, "learning_rate": 1.0648039457893626e-05, "loss": 1.1015, "step": 258 }, { "epoch": 2.649616368286445, "grad_norm": 0.132588019525129, "learning_rate": 1.0576119838245843e-05, "loss": 1.1136, "step": 259 }, { "epoch": 2.659846547314578, "grad_norm": 0.10788892264634141, "learning_rate": 1.050417030713075e-05, "loss": 1.1122, "step": 260 }, { "epoch": 2.670076726342711, "grad_norm": 0.1394237118791102, "learning_rate": 1.043219460008374e-05, "loss": 1.096, "step": 261 }, { "epoch": 2.680306905370844, "grad_norm": 0.10732412252502514, "learning_rate": 1.0360196453999236e-05, "loss": 1.0954, "step": 262 }, { "epoch": 2.690537084398977, "grad_norm": 0.1300254875907006, "learning_rate": 1.0288179606936666e-05, "loss": 1.0993, "step": 263 }, { "epoch": 2.70076726342711, "grad_norm": 0.13557134535284363, "learning_rate": 1.0216147797926387e-05, "loss": 1.1009, "step": 264 }, { "epoch": 2.710997442455243, "grad_norm": 0.10517607316623458, "learning_rate": 1.0144104766775574e-05, "loss": 1.1054, "step": 265 }, { "epoch": 2.7212276214833757, "grad_norm": 0.11762585297069877, "learning_rate": 1.0072054253874027e-05, "loss": 1.1254, "step": 266 }, { "epoch": 2.731457800511509, "grad_norm": 0.1018754367413057, "learning_rate": 1e-05, "loss": 1.1077, "step": 267 }, { "epoch": 2.741687979539642, "grad_norm": 0.10732203679139746, "learning_rate": 9.927945746125975e-06, "loss": 1.1049, "step": 268 }, { "epoch": 2.7519181585677748, "grad_norm": 0.10466211118133831, "learning_rate": 9.855895233224431e-06, "loss": 1.1218, "step": 269 }, { "epoch": 2.762148337595908, "grad_norm": 0.10130418761164744, "learning_rate": 9.783852202073614e-06, "loss": 1.094, "step": 270 }, { "epoch": 2.772378516624041, "grad_norm": 0.10945930003301446, "learning_rate": 9.711820393063337e-06, "loss": 1.1022, "step": 271 }, { "epoch": 2.782608695652174, "grad_norm": 0.1075929626116382, "learning_rate": 9.639803546000767e-06, "loss": 1.0962, "step": 272 }, { "epoch": 2.792838874680307, "grad_norm": 0.12358843987367081, "learning_rate": 9.56780539991626e-06, "loss": 1.095, "step": 273 }, { "epoch": 2.80306905370844, "grad_norm": 0.10925745237435609, "learning_rate": 9.495829692869255e-06, "loss": 1.1106, "step": 274 }, { "epoch": 2.813299232736573, "grad_norm": 0.14899968501585512, "learning_rate": 9.423880161754158e-06, "loss": 1.1158, "step": 275 }, { "epoch": 2.8235294117647056, "grad_norm": 0.10491437060128686, "learning_rate": 9.351960542106375e-06, "loss": 1.1128, "step": 276 }, { "epoch": 2.833759590792839, "grad_norm": 0.12716295581716067, "learning_rate": 9.28007456790833e-06, "loss": 1.1081, "step": 277 }, { "epoch": 2.843989769820972, "grad_norm": 0.09991905391073584, "learning_rate": 9.208225971395618e-06, "loss": 1.1088, "step": 278 }, { "epoch": 2.8542199488491047, "grad_norm": 0.10457918154389038, "learning_rate": 9.13641848286323e-06, "loss": 1.1003, "step": 279 }, { "epoch": 2.864450127877238, "grad_norm": 0.12988874919136506, "learning_rate": 9.064655830471871e-06, "loss": 1.1048, "step": 280 }, { "epoch": 2.874680306905371, "grad_norm": 0.08950534866894107, "learning_rate": 8.992941740054418e-06, "loss": 1.1068, "step": 281 }, { "epoch": 2.8849104859335037, "grad_norm": 0.12496894290714236, "learning_rate": 8.921279934922463e-06, "loss": 1.1042, "step": 282 }, { "epoch": 2.895140664961637, "grad_norm": 0.08980237782541681, "learning_rate": 8.849674135672999e-06, "loss": 1.0948, "step": 283 }, { "epoch": 2.90537084398977, "grad_norm": 0.1045096765288442, "learning_rate": 8.778128059995269e-06, "loss": 1.0949, "step": 284 }, { "epoch": 2.915601023017903, "grad_norm": 0.0942911320577268, "learning_rate": 8.706645422477739e-06, "loss": 1.1063, "step": 285 }, { "epoch": 2.9258312020460355, "grad_norm": 0.09732837098228204, "learning_rate": 8.63522993441523e-06, "loss": 1.1024, "step": 286 }, { "epoch": 2.9360613810741687, "grad_norm": 0.10890274488534847, "learning_rate": 8.563885303616253e-06, "loss": 1.1063, "step": 287 }, { "epoch": 2.946291560102302, "grad_norm": 0.09902129351000988, "learning_rate": 8.492615234210483e-06, "loss": 1.111, "step": 288 }, { "epoch": 2.9565217391304346, "grad_norm": 0.10108963082886802, "learning_rate": 8.42142342645646e-06, "loss": 1.1186, "step": 289 }, { "epoch": 2.9667519181585678, "grad_norm": 0.09639164159442688, "learning_rate": 8.350313576549477e-06, "loss": 1.1035, "step": 290 }, { "epoch": 2.976982097186701, "grad_norm": 0.10435027450467657, "learning_rate": 8.279289376429653e-06, "loss": 1.0997, "step": 291 }, { "epoch": 2.9872122762148337, "grad_norm": 0.11694161353696701, "learning_rate": 8.20835451359029e-06, "loss": 1.1202, "step": 292 }, { "epoch": 2.997442455242967, "grad_norm": 0.12691770351783396, "learning_rate": 8.137512670886397e-06, "loss": 1.2833, "step": 293 }, { "epoch": 3.0076726342710995, "grad_norm": 0.1380023630900202, "learning_rate": 8.066767526343477e-06, "loss": 1.2203, "step": 294 }, { "epoch": 3.0179028132992327, "grad_norm": 0.11233227592140108, "learning_rate": 7.996122752966596e-06, "loss": 1.0977, "step": 295 }, { "epoch": 3.028132992327366, "grad_norm": 0.13228152412358327, "learning_rate": 7.925582018549642e-06, "loss": 1.1102, "step": 296 }, { "epoch": 3.0383631713554986, "grad_norm": 0.08943425137344732, "learning_rate": 7.855148985484946e-06, "loss": 1.0857, "step": 297 }, { "epoch": 3.0485933503836318, "grad_norm": 0.12414532914388172, "learning_rate": 7.784827310573101e-06, "loss": 1.0889, "step": 298 }, { "epoch": 3.0588235294117645, "grad_norm": 0.09196642831574475, "learning_rate": 7.71462064483311e-06, "loss": 1.102, "step": 299 }, { "epoch": 3.0690537084398977, "grad_norm": 0.1066153403799132, "learning_rate": 7.644532633312842e-06, "loss": 1.1058, "step": 300 }, { "epoch": 3.079283887468031, "grad_norm": 0.0952781707829241, "learning_rate": 7.574566914899779e-06, "loss": 1.1038, "step": 301 }, { "epoch": 3.0895140664961636, "grad_norm": 0.11931361107051638, "learning_rate": 7.504727122132078e-06, "loss": 1.1304, "step": 302 }, { "epoch": 3.0997442455242967, "grad_norm": 0.10197813711960663, "learning_rate": 7.4350168810099955e-06, "loss": 1.0866, "step": 303 }, { "epoch": 3.10997442455243, "grad_norm": 0.10840833371271409, "learning_rate": 7.365439810807609e-06, "loss": 1.115, "step": 304 }, { "epoch": 3.1202046035805626, "grad_norm": 0.10054202025269407, "learning_rate": 7.295999523884921e-06, "loss": 1.1127, "step": 305 }, { "epoch": 3.130434782608696, "grad_norm": 0.08600891877130412, "learning_rate": 7.226699625500317e-06, "loss": 1.0785, "step": 306 }, { "epoch": 3.1406649616368285, "grad_norm": 0.09585720988122803, "learning_rate": 7.157543713623353e-06, "loss": 1.1001, "step": 307 }, { "epoch": 3.1508951406649617, "grad_norm": 0.09650179492525698, "learning_rate": 7.088535378747991e-06, "loss": 1.1062, "step": 308 }, { "epoch": 3.1611253196930944, "grad_norm": 0.10968991795087037, "learning_rate": 7.019678203706164e-06, "loss": 1.125, "step": 309 }, { "epoch": 3.1713554987212276, "grad_norm": 0.08459389639753583, "learning_rate": 6.950975763481758e-06, "loss": 1.0933, "step": 310 }, { "epoch": 3.1815856777493607, "grad_norm": 0.1067018403754317, "learning_rate": 6.882431625025016e-06, "loss": 1.0808, "step": 311 }, { "epoch": 3.1918158567774935, "grad_norm": 0.08627293417890422, "learning_rate": 6.81404934706733e-06, "loss": 1.096, "step": 312 }, { "epoch": 3.2020460358056266, "grad_norm": 0.1203602623645767, "learning_rate": 6.745832479936492e-06, "loss": 1.0989, "step": 313 }, { "epoch": 3.21227621483376, "grad_norm": 0.09084694505769592, "learning_rate": 6.677784565372359e-06, "loss": 1.0754, "step": 314 }, { "epoch": 3.2225063938618925, "grad_norm": 0.1021182704289713, "learning_rate": 6.609909136342956e-06, "loss": 1.1069, "step": 315 }, { "epoch": 3.2327365728900257, "grad_norm": 0.08402095747413522, "learning_rate": 6.542209716861074e-06, "loss": 1.0903, "step": 316 }, { "epoch": 3.2429667519181584, "grad_norm": 0.09500966609097991, "learning_rate": 6.474689821801295e-06, "loss": 1.0801, "step": 317 }, { "epoch": 3.2531969309462916, "grad_norm": 0.07999388340423734, "learning_rate": 6.407352956717489e-06, "loss": 1.0966, "step": 318 }, { "epoch": 3.2634271099744243, "grad_norm": 0.08167568278859896, "learning_rate": 6.340202617660842e-06, "loss": 1.0899, "step": 319 }, { "epoch": 3.2736572890025575, "grad_norm": 0.1063636695839879, "learning_rate": 6.2732422909983116e-06, "loss": 1.1136, "step": 320 }, { "epoch": 3.2838874680306906, "grad_norm": 0.08988026127508021, "learning_rate": 6.206475453231644e-06, "loss": 1.1008, "step": 321 }, { "epoch": 3.2941176470588234, "grad_norm": 0.08402419613939409, "learning_rate": 6.1399055708168675e-06, "loss": 1.0968, "step": 322 }, { "epoch": 3.3043478260869565, "grad_norm": 0.08473579812883723, "learning_rate": 6.073536099984314e-06, "loss": 1.086, "step": 323 }, { "epoch": 3.3145780051150897, "grad_norm": 0.09065011802077148, "learning_rate": 6.007370486559185e-06, "loss": 1.0826, "step": 324 }, { "epoch": 3.3248081841432224, "grad_norm": 0.08123796637404178, "learning_rate": 5.941412165782645e-06, "loss": 1.0987, "step": 325 }, { "epoch": 3.3350383631713556, "grad_norm": 0.07861932284651663, "learning_rate": 5.875664562133462e-06, "loss": 1.0937, "step": 326 }, { "epoch": 3.3452685421994883, "grad_norm": 0.0877093327642083, "learning_rate": 5.810131089150228e-06, "loss": 1.0799, "step": 327 }, { "epoch": 3.3554987212276215, "grad_norm": 0.0875672287388788, "learning_rate": 5.7448151492541025e-06, "loss": 1.1029, "step": 328 }, { "epoch": 3.3657289002557547, "grad_norm": 0.08135002167340141, "learning_rate": 5.6797201335722064e-06, "loss": 1.0869, "step": 329 }, { "epoch": 3.3759590792838874, "grad_norm": 0.08353184508759956, "learning_rate": 5.6148494217615136e-06, "loss": 1.0991, "step": 330 }, { "epoch": 3.3861892583120206, "grad_norm": 0.08789822412537054, "learning_rate": 5.550206381833409e-06, "loss": 1.0826, "step": 331 }, { "epoch": 3.3964194373401533, "grad_norm": 0.07456550505190995, "learning_rate": 5.485794369978828e-06, "loss": 1.0895, "step": 332 }, { "epoch": 3.4066496163682864, "grad_norm": 0.07944242106726856, "learning_rate": 5.421616730394e-06, "loss": 1.1061, "step": 333 }, { "epoch": 3.4168797953964196, "grad_norm": 0.07546741635902159, "learning_rate": 5.357676795106798e-06, "loss": 1.1018, "step": 334 }, { "epoch": 3.4271099744245523, "grad_norm": 0.08310249336045959, "learning_rate": 5.293977883803797e-06, "loss": 1.0945, "step": 335 }, { "epoch": 3.4373401534526855, "grad_norm": 0.0812640296608218, "learning_rate": 5.230523303657861e-06, "loss": 1.1026, "step": 336 }, { "epoch": 3.4475703324808182, "grad_norm": 0.07328532212644745, "learning_rate": 5.167316349156495e-06, "loss": 1.1008, "step": 337 }, { "epoch": 3.4578005115089514, "grad_norm": 0.08950488186559938, "learning_rate": 5.104360301930744e-06, "loss": 1.1223, "step": 338 }, { "epoch": 3.4680306905370846, "grad_norm": 0.08444810532033332, "learning_rate": 5.041658430584852e-06, "loss": 1.0866, "step": 339 }, { "epoch": 3.4782608695652173, "grad_norm": 0.07487349055804385, "learning_rate": 4.979213990526558e-06, "loss": 1.1065, "step": 340 }, { "epoch": 3.4884910485933505, "grad_norm": 0.08374959015248361, "learning_rate": 4.917030223798057e-06, "loss": 1.0936, "step": 341 }, { "epoch": 3.498721227621483, "grad_norm": 0.08135128819521088, "learning_rate": 4.855110358907689e-06, "loss": 1.1046, "step": 342 }, { "epoch": 3.5089514066496164, "grad_norm": 0.08162603384620307, "learning_rate": 4.793457610662334e-06, "loss": 1.1222, "step": 343 }, { "epoch": 3.5191815856777495, "grad_norm": 0.09283118907374514, "learning_rate": 4.732075180000473e-06, "loss": 1.08, "step": 344 }, { "epoch": 3.5294117647058822, "grad_norm": 0.07847795827036227, "learning_rate": 4.670966253826027e-06, "loss": 1.1049, "step": 345 }, { "epoch": 3.5396419437340154, "grad_norm": 0.08347427138149979, "learning_rate": 4.610134004842876e-06, "loss": 1.1178, "step": 346 }, { "epoch": 3.5498721227621486, "grad_norm": 0.08293810876881759, "learning_rate": 4.549581591390142e-06, "loss": 1.0957, "step": 347 }, { "epoch": 3.5601023017902813, "grad_norm": 0.07860719161002713, "learning_rate": 4.489312157278227e-06, "loss": 1.1041, "step": 348 }, { "epoch": 3.5703324808184145, "grad_norm": 0.0776274148549742, "learning_rate": 4.429328831625565e-06, "loss": 1.1022, "step": 349 }, { "epoch": 3.580562659846547, "grad_norm": 0.08129431944882311, "learning_rate": 4.369634728696175e-06, "loss": 1.101, "step": 350 }, { "epoch": 3.5907928388746804, "grad_norm": 0.0828602633677553, "learning_rate": 4.310232947737979e-06, "loss": 1.0906, "step": 351 }, { "epoch": 3.601023017902813, "grad_norm": 0.08541653068532609, "learning_rate": 4.251126572821876e-06, "loss": 1.1075, "step": 352 }, { "epoch": 3.6112531969309463, "grad_norm": 0.08051287162548261, "learning_rate": 4.192318672681631e-06, "loss": 1.0896, "step": 353 }, { "epoch": 3.6214833759590794, "grad_norm": 0.08331284457296466, "learning_rate": 4.133812300554555e-06, "loss": 1.0915, "step": 354 }, { "epoch": 3.631713554987212, "grad_norm": 0.0814302719831979, "learning_rate": 4.0756104940229645e-06, "loss": 1.0972, "step": 355 }, { "epoch": 3.6419437340153453, "grad_norm": 0.07546517962940778, "learning_rate": 4.017716274856503e-06, "loss": 1.0915, "step": 356 }, { "epoch": 3.6521739130434785, "grad_norm": 0.08021341106443662, "learning_rate": 3.960132648855226e-06, "loss": 1.0946, "step": 357 }, { "epoch": 3.662404092071611, "grad_norm": 0.07723812404280248, "learning_rate": 3.902862605693557e-06, "loss": 1.1073, "step": 358 }, { "epoch": 3.6726342710997444, "grad_norm": 0.08388920809519412, "learning_rate": 3.845909118765073e-06, "loss": 1.0852, "step": 359 }, { "epoch": 3.682864450127877, "grad_norm": 0.07847283754334586, "learning_rate": 3.7892751450281162e-06, "loss": 1.0991, "step": 360 }, { "epoch": 3.6930946291560103, "grad_norm": 0.07780759853065682, "learning_rate": 3.732963624852275e-06, "loss": 1.0827, "step": 361 }, { "epoch": 3.703324808184143, "grad_norm": 0.0803660841644063, "learning_rate": 3.6769774818657376e-06, "loss": 1.097, "step": 362 }, { "epoch": 3.713554987212276, "grad_norm": 0.07612406512756861, "learning_rate": 3.6213196228034796e-06, "loss": 1.0871, "step": 363 }, { "epoch": 3.7237851662404093, "grad_norm": 0.07299998674494353, "learning_rate": 3.5659929373563586e-06, "loss": 1.0892, "step": 364 }, { "epoch": 3.734015345268542, "grad_norm": 0.07553174968861515, "learning_rate": 3.511000298021098e-06, "loss": 1.1067, "step": 365 }, { "epoch": 3.7442455242966752, "grad_norm": 0.0770305266723946, "learning_rate": 3.4563445599511225e-06, "loss": 1.0884, "step": 366 }, { "epoch": 3.7544757033248084, "grad_norm": 0.06828213495807446, "learning_rate": 3.402028560808357e-06, "loss": 1.0905, "step": 367 }, { "epoch": 3.764705882352941, "grad_norm": 0.07174302293960781, "learning_rate": 3.348055120615854e-06, "loss": 1.0953, "step": 368 }, { "epoch": 3.7749360613810743, "grad_norm": 0.07065151561263502, "learning_rate": 3.2944270416114256e-06, "loss": 1.0934, "step": 369 }, { "epoch": 3.785166240409207, "grad_norm": 0.0745468761667153, "learning_rate": 3.241147108102135e-06, "loss": 1.0788, "step": 370 }, { "epoch": 3.79539641943734, "grad_norm": 0.0793558844392241, "learning_rate": 3.1882180863197308e-06, "loss": 1.1129, "step": 371 }, { "epoch": 3.805626598465473, "grad_norm": 0.07353357138806105, "learning_rate": 3.135642724277036e-06, "loss": 1.1119, "step": 372 }, { "epoch": 3.815856777493606, "grad_norm": 0.06934149579578255, "learning_rate": 3.0834237516252817e-06, "loss": 1.0964, "step": 373 }, { "epoch": 3.8260869565217392, "grad_norm": 0.07863469621941148, "learning_rate": 3.0315638795123726e-06, "loss": 1.1096, "step": 374 }, { "epoch": 3.836317135549872, "grad_norm": 0.07819919836274157, "learning_rate": 2.980065800442137e-06, "loss": 1.0894, "step": 375 }, { "epoch": 3.846547314578005, "grad_norm": 0.068621285991009, "learning_rate": 2.9289321881345257e-06, "loss": 1.0929, "step": 376 }, { "epoch": 3.8567774936061383, "grad_norm": 0.07596287188263177, "learning_rate": 2.878165697386812e-06, "loss": 1.113, "step": 377 }, { "epoch": 3.867007672634271, "grad_norm": 0.07944342025232361, "learning_rate": 2.8277689639357453e-06, "loss": 1.0877, "step": 378 }, { "epoch": 3.877237851662404, "grad_norm": 0.07100330530945316, "learning_rate": 2.777744604320706e-06, "loss": 1.0888, "step": 379 }, { "epoch": 3.887468030690537, "grad_norm": 0.07285101223673769, "learning_rate": 2.7280952157478592e-06, "loss": 1.1291, "step": 380 }, { "epoch": 3.89769820971867, "grad_norm": 0.07792682033692153, "learning_rate": 2.678823375955314e-06, "loss": 1.0649, "step": 381 }, { "epoch": 3.907928388746803, "grad_norm": 0.0715111413196263, "learning_rate": 2.6299316430792955e-06, "loss": 1.112, "step": 382 }, { "epoch": 3.918158567774936, "grad_norm": 0.07648789767821362, "learning_rate": 2.581422555521316e-06, "loss": 1.0902, "step": 383 }, { "epoch": 3.928388746803069, "grad_norm": 0.07128773050766629, "learning_rate": 2.5332986318163887e-06, "loss": 1.0983, "step": 384 }, { "epoch": 3.938618925831202, "grad_norm": 0.0682438885651234, "learning_rate": 2.485562370502279e-06, "loss": 1.0889, "step": 385 }, { "epoch": 3.948849104859335, "grad_norm": 0.07287814936389599, "learning_rate": 2.4382162499897743e-06, "loss": 1.0802, "step": 386 }, { "epoch": 3.959079283887468, "grad_norm": 0.07052025847974024, "learning_rate": 2.391262728433995e-06, "loss": 1.0856, "step": 387 }, { "epoch": 3.969309462915601, "grad_norm": 0.06970550208748211, "learning_rate": 2.3447042436068013e-06, "loss": 1.1261, "step": 388 }, { "epoch": 3.979539641943734, "grad_norm": 0.0661486634983042, "learning_rate": 2.2985432127701945e-06, "loss": 1.1114, "step": 389 }, { "epoch": 3.9897698209718673, "grad_norm": 0.07304435441931525, "learning_rate": 2.2527820325508445e-06, "loss": 1.0964, "step": 390 }, { "epoch": 4.0, "grad_norm": 0.08918770589438005, "learning_rate": 2.2074230788156325e-06, "loss": 1.3834, "step": 391 }, { "epoch": 4.010230179028133, "grad_norm": 0.06793128931714114, "learning_rate": 2.162468706548314e-06, "loss": 1.0806, "step": 392 }, { "epoch": 4.020460358056266, "grad_norm": 0.07095445398272698, "learning_rate": 2.1179212497272582e-06, "loss": 1.0952, "step": 393 }, { "epoch": 4.030690537084399, "grad_norm": 0.06939795350559927, "learning_rate": 2.073783021204251e-06, "loss": 1.0872, "step": 394 }, { "epoch": 4.040920716112532, "grad_norm": 0.07028155944155796, "learning_rate": 2.030056312584424e-06, "loss": 1.0949, "step": 395 }, { "epoch": 4.051150895140665, "grad_norm": 0.06522291450234556, "learning_rate": 1.9867433941072857e-06, "loss": 1.0809, "step": 396 }, { "epoch": 4.061381074168798, "grad_norm": 0.07196334365349571, "learning_rate": 1.9438465145288377e-06, "loss": 1.0836, "step": 397 }, { "epoch": 4.071611253196931, "grad_norm": 0.08064330392371075, "learning_rate": 1.9013679010048292e-06, "loss": 1.1097, "step": 398 }, { "epoch": 4.081841432225064, "grad_norm": 0.06571773302817012, "learning_rate": 1.8593097589751318e-06, "loss": 1.111, "step": 399 }, { "epoch": 4.092071611253197, "grad_norm": 0.062276311430290957, "learning_rate": 1.8176742720492213e-06, "loss": 1.0819, "step": 400 }, { "epoch": 4.10230179028133, "grad_norm": 0.0642977513734688, "learning_rate": 1.7764636018928249e-06, "loss": 1.088, "step": 401 }, { "epoch": 4.112531969309463, "grad_norm": 0.0637350396800773, "learning_rate": 1.7356798881156734e-06, "loss": 1.0879, "step": 402 }, { "epoch": 4.122762148337596, "grad_norm": 0.06721366550621166, "learning_rate": 1.6953252481604198e-06, "loss": 1.0902, "step": 403 }, { "epoch": 4.132992327365729, "grad_norm": 0.06948641112376654, "learning_rate": 1.655401777192719e-06, "loss": 1.0986, "step": 404 }, { "epoch": 4.143222506393862, "grad_norm": 0.0626221328219274, "learning_rate": 1.6159115479924259e-06, "loss": 1.0905, "step": 405 }, { "epoch": 4.153452685421995, "grad_norm": 0.06456343231204456, "learning_rate": 1.5768566108459916e-06, "loss": 1.0975, "step": 406 }, { "epoch": 4.163682864450128, "grad_norm": 0.06688597005712824, "learning_rate": 1.5382389934400199e-06, "loss": 1.098, "step": 407 }, { "epoch": 4.173913043478261, "grad_norm": 0.06517025632049872, "learning_rate": 1.5000607007559797e-06, "loss": 1.106, "step": 408 }, { "epoch": 4.1841432225063935, "grad_norm": 0.07241413465365451, "learning_rate": 1.462323714966114e-06, "loss": 1.1056, "step": 409 }, { "epoch": 4.194373401534527, "grad_norm": 0.0626591365200779, "learning_rate": 1.4250299953305368e-06, "loss": 1.0909, "step": 410 }, { "epoch": 4.20460358056266, "grad_norm": 0.06290433735967586, "learning_rate": 1.3881814780954916e-06, "loss": 1.0862, "step": 411 }, { "epoch": 4.2148337595907925, "grad_norm": 0.06562548066395703, "learning_rate": 1.3517800763928457e-06, "loss": 1.085, "step": 412 }, { "epoch": 4.225063938618926, "grad_norm": 0.07230120985354872, "learning_rate": 1.3158276801407432e-06, "loss": 1.0836, "step": 413 }, { "epoch": 4.235294117647059, "grad_norm": 0.06902008367696279, "learning_rate": 1.2803261559454905e-06, "loss": 1.1007, "step": 414 }, { "epoch": 4.245524296675192, "grad_norm": 0.06588908862612752, "learning_rate": 1.2452773470046543e-06, "loss": 1.0984, "step": 415 }, { "epoch": 4.255754475703325, "grad_norm": 0.063137709191012, "learning_rate": 1.2106830730113462e-06, "loss": 1.0946, "step": 416 }, { "epoch": 4.265984654731458, "grad_norm": 0.07102555153508887, "learning_rate": 1.1765451300597574e-06, "loss": 1.0805, "step": 417 }, { "epoch": 4.276214833759591, "grad_norm": 0.06467253916745043, "learning_rate": 1.14286529055191e-06, "loss": 1.0901, "step": 418 }, { "epoch": 4.286445012787723, "grad_norm": 0.06915106095726498, "learning_rate": 1.1096453031056265e-06, "loss": 1.0769, "step": 419 }, { "epoch": 4.296675191815857, "grad_norm": 0.062046225324203945, "learning_rate": 1.0768868924637555e-06, "loss": 1.1005, "step": 420 }, { "epoch": 4.30690537084399, "grad_norm": 0.06161050910758704, "learning_rate": 1.0445917594046073e-06, "loss": 1.1091, "step": 421 }, { "epoch": 4.3171355498721224, "grad_norm": 0.06840440829273428, "learning_rate": 1.012761580653674e-06, "loss": 1.0793, "step": 422 }, { "epoch": 4.327365728900256, "grad_norm": 0.06545455107706256, "learning_rate": 9.813980087965625e-07, "loss": 1.0966, "step": 423 }, { "epoch": 4.337595907928389, "grad_norm": 0.0656253445318609, "learning_rate": 9.505026721931898e-07, "loss": 1.0981, "step": 424 }, { "epoch": 4.3478260869565215, "grad_norm": 0.06159289128517746, "learning_rate": 9.200771748932513e-07, "loss": 1.0855, "step": 425 }, { "epoch": 4.358056265984655, "grad_norm": 0.06283637377188069, "learning_rate": 8.901230965529383e-07, "loss": 1.0914, "step": 426 }, { "epoch": 4.368286445012788, "grad_norm": 0.05874494449881211, "learning_rate": 8.606419923529175e-07, "loss": 1.0959, "step": 427 }, { "epoch": 4.378516624040921, "grad_norm": 0.06757842029553479, "learning_rate": 8.316353929175935e-07, "loss": 1.1129, "step": 428 }, { "epoch": 4.388746803069053, "grad_norm": 0.06453926787295151, "learning_rate": 8.031048042356393e-07, "loss": 1.0966, "step": 429 }, { "epoch": 4.398976982097187, "grad_norm": 0.060136006600051944, "learning_rate": 7.750517075818064e-07, "loss": 1.0956, "step": 430 }, { "epoch": 4.40920716112532, "grad_norm": 0.06544195360547111, "learning_rate": 7.474775594400252e-07, "loss": 1.1075, "step": 431 }, { "epoch": 4.419437340153452, "grad_norm": 0.05953534472724859, "learning_rate": 7.203837914277689e-07, "loss": 1.0893, "step": 432 }, { "epoch": 4.429667519181586, "grad_norm": 0.061720039915185494, "learning_rate": 6.937718102217461e-07, "loss": 1.0919, "step": 433 }, { "epoch": 4.439897698209719, "grad_norm": 0.06185148007425812, "learning_rate": 6.676429974848564e-07, "loss": 1.1045, "step": 434 }, { "epoch": 4.450127877237851, "grad_norm": 0.06383916159735249, "learning_rate": 6.41998709794458e-07, "loss": 1.0874, "step": 435 }, { "epoch": 4.460358056265985, "grad_norm": 0.06432196372458962, "learning_rate": 6.168402785719351e-07, "loss": 1.0946, "step": 436 }, { "epoch": 4.470588235294118, "grad_norm": 0.06371318505406906, "learning_rate": 5.921690100135713e-07, "loss": 1.0952, "step": 437 }, { "epoch": 4.4808184143222505, "grad_norm": 0.06331390223722556, "learning_rate": 5.67986185022743e-07, "loss": 1.1013, "step": 438 }, { "epoch": 4.491048593350383, "grad_norm": 0.06245277006985015, "learning_rate": 5.442930591433992e-07, "loss": 1.103, "step": 439 }, { "epoch": 4.501278772378517, "grad_norm": 0.06212144520591636, "learning_rate": 5.210908624948896e-07, "loss": 1.0891, "step": 440 }, { "epoch": 4.5115089514066495, "grad_norm": 0.05914162274935749, "learning_rate": 4.983807997080925e-07, "loss": 1.1037, "step": 441 }, { "epoch": 4.521739130434782, "grad_norm": 0.05987051434535725, "learning_rate": 4.76164049862875e-07, "loss": 1.101, "step": 442 }, { "epoch": 4.531969309462916, "grad_norm": 0.05918609588639192, "learning_rate": 4.544417664268652e-07, "loss": 1.0863, "step": 443 }, { "epoch": 4.542199488491049, "grad_norm": 0.0646266545167014, "learning_rate": 4.332150771955845e-07, "loss": 1.0799, "step": 444 }, { "epoch": 4.552429667519181, "grad_norm": 0.06792492927332083, "learning_rate": 4.124850842338779e-07, "loss": 1.0984, "step": 445 }, { "epoch": 4.562659846547315, "grad_norm": 0.06609066214024004, "learning_rate": 3.92252863818704e-07, "loss": 1.1065, "step": 446 }, { "epoch": 4.572890025575448, "grad_norm": 0.06329374872265735, "learning_rate": 3.725194663832521e-07, "loss": 1.0779, "step": 447 }, { "epoch": 4.58312020460358, "grad_norm": 0.05726355362639091, "learning_rate": 3.5328591646240695e-07, "loss": 1.1035, "step": 448 }, { "epoch": 4.593350383631714, "grad_norm": 0.059407424800830735, "learning_rate": 3.345532126395579e-07, "loss": 1.0867, "step": 449 }, { "epoch": 4.603580562659847, "grad_norm": 0.059305586628798, "learning_rate": 3.163223274947491e-07, "loss": 1.0922, "step": 450 }, { "epoch": 4.6138107416879794, "grad_norm": 0.06071987601352744, "learning_rate": 2.985942075541848e-07, "loss": 1.0697, "step": 451 }, { "epoch": 4.624040920716112, "grad_norm": 0.06292255955807154, "learning_rate": 2.813697732410947e-07, "loss": 1.0981, "step": 452 }, { "epoch": 4.634271099744246, "grad_norm": 0.06082661629174749, "learning_rate": 2.646499188279328e-07, "loss": 1.1036, "step": 453 }, { "epoch": 4.6445012787723785, "grad_norm": 0.06338862205836374, "learning_rate": 2.48435512389964e-07, "loss": 1.1061, "step": 454 }, { "epoch": 4.654731457800511, "grad_norm": 0.06111031646331084, "learning_rate": 2.3272739576017945e-07, "loss": 1.0925, "step": 455 }, { "epoch": 4.664961636828645, "grad_norm": 0.06409358126771195, "learning_rate": 2.1752638448559793e-07, "loss": 1.0858, "step": 456 }, { "epoch": 4.675191815856778, "grad_norm": 0.05919714440459587, "learning_rate": 2.028332677849254e-07, "loss": 1.0808, "step": 457 }, { "epoch": 4.68542199488491, "grad_norm": 0.06294639466037077, "learning_rate": 1.8864880850757327e-07, "loss": 1.0997, "step": 458 }, { "epoch": 4.695652173913043, "grad_norm": 0.05824766217072136, "learning_rate": 1.7497374309405346e-07, "loss": 1.1121, "step": 459 }, { "epoch": 4.705882352941177, "grad_norm": 0.05899681478258629, "learning_rate": 1.6180878153775114e-07, "loss": 1.0868, "step": 460 }, { "epoch": 4.716112531969309, "grad_norm": 0.05647415773366634, "learning_rate": 1.49154607348051e-07, "loss": 1.0873, "step": 461 }, { "epoch": 4.726342710997442, "grad_norm": 0.06300014638540047, "learning_rate": 1.3701187751485655e-07, "loss": 1.1027, "step": 462 }, { "epoch": 4.736572890025576, "grad_norm": 0.05856455782981277, "learning_rate": 1.2538122247448325e-07, "loss": 1.097, "step": 463 }, { "epoch": 4.746803069053708, "grad_norm": 0.06043711673007517, "learning_rate": 1.1426324607691774e-07, "loss": 1.1013, "step": 464 }, { "epoch": 4.757033248081841, "grad_norm": 0.05634145088734339, "learning_rate": 1.0365852555447642e-07, "loss": 1.0969, "step": 465 }, { "epoch": 4.767263427109975, "grad_norm": 0.06039111682514058, "learning_rate": 9.356761149182714e-08, "loss": 1.1086, "step": 466 }, { "epoch": 4.7774936061381075, "grad_norm": 0.060023127561203406, "learning_rate": 8.39910277974132e-08, "loss": 1.0913, "step": 467 }, { "epoch": 4.78772378516624, "grad_norm": 0.06215604952469197, "learning_rate": 7.492927167624286e-08, "loss": 1.1019, "step": 468 }, { "epoch": 4.797953964194374, "grad_norm": 0.05702610188845003, "learning_rate": 6.638281360408339e-08, "loss": 1.0753, "step": 469 }, { "epoch": 4.8081841432225065, "grad_norm": 0.0596592285939729, "learning_rate": 5.8352097303027155e-08, "loss": 1.0878, "step": 470 }, { "epoch": 4.818414322250639, "grad_norm": 0.06020706510477553, "learning_rate": 5.083753971846239e-08, "loss": 1.0823, "step": 471 }, { "epoch": 4.828644501278772, "grad_norm": 0.06317187530774661, "learning_rate": 4.383953099741711e-08, "loss": 1.0976, "step": 472 }, { "epoch": 4.838874680306906, "grad_norm": 0.058558480847157236, "learning_rate": 3.735843446830867e-08, "loss": 1.08, "step": 473 }, { "epoch": 4.849104859335038, "grad_norm": 0.06411026525300602, "learning_rate": 3.139458662207995e-08, "loss": 1.0861, "step": 474 }, { "epoch": 4.859335038363171, "grad_norm": 0.05895579449215754, "learning_rate": 2.5948297094724463e-08, "loss": 1.1006, "step": 475 }, { "epoch": 4.869565217391305, "grad_norm": 0.062375184231428585, "learning_rate": 2.10198486512192e-08, "loss": 1.0962, "step": 476 }, { "epoch": 4.879795396419437, "grad_norm": 0.061993219240511176, "learning_rate": 1.6609497170834154e-08, "loss": 1.1038, "step": 477 }, { "epoch": 4.89002557544757, "grad_norm": 0.06097444925998557, "learning_rate": 1.2717471633852951e-08, "loss": 1.0991, "step": 478 }, { "epoch": 4.900255754475703, "grad_norm": 0.06357626872394341, "learning_rate": 9.343974109685684e-09, "loss": 1.1042, "step": 479 }, { "epoch": 4.910485933503836, "grad_norm": 0.06017489250587178, "learning_rate": 6.489179746370644e-09, "loss": 1.0812, "step": 480 }, { "epoch": 4.920716112531969, "grad_norm": 0.06216550447937654, "learning_rate": 4.153236761488266e-09, "loss": 1.0885, "step": 481 }, { "epoch": 4.930946291560103, "grad_norm": 0.06156610049084557, "learning_rate": 2.336266434463941e-09, "loss": 1.1078, "step": 482 }, { "epoch": 4.9411764705882355, "grad_norm": 0.059717243216370564, "learning_rate": 1.0383631002686133e-09, "loss": 1.1129, "step": 483 }, { "epoch": 4.951406649616368, "grad_norm": 0.06208309325116676, "learning_rate": 2.5959414452270126e-10, "loss": 1.0837, "step": 484 }, { "epoch": 4.961636828644501, "grad_norm": 0.05969057991500395, "learning_rate": 0.0, "loss": 1.0921, "step": 485 }, { "epoch": 4.961636828644501, "step": 485, "total_flos": 7065760181780480.0, "train_loss": 1.1421357911886627, "train_runtime": 42611.7003, "train_samples_per_second": 11.734, "train_steps_per_second": 0.011 } ], "logging_steps": 1.0, "max_steps": 485, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 7065760181780480.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }