{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 441, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0022695035460992908, "grad_norm": 11.980184555053711, "learning_rate": 0.0, "loss": 2.2009, "step": 1 }, { "epoch": 0.0045390070921985815, "grad_norm": 10.250102996826172, "learning_rate": 2.0000000000000003e-06, "loss": 2.0865, "step": 2 }, { "epoch": 0.006808510638297872, "grad_norm": 9.704007148742676, "learning_rate": 4.000000000000001e-06, "loss": 2.197, "step": 3 }, { "epoch": 0.009078014184397163, "grad_norm": 10.862658500671387, "learning_rate": 6e-06, "loss": 2.2891, "step": 4 }, { "epoch": 0.011347517730496455, "grad_norm": 7.258336544036865, "learning_rate": 8.000000000000001e-06, "loss": 1.9288, "step": 5 }, { "epoch": 0.013617021276595745, "grad_norm": 6.688610076904297, "learning_rate": 1e-05, "loss": 1.877, "step": 6 }, { "epoch": 0.015886524822695036, "grad_norm": 5.704906463623047, "learning_rate": 9.977064220183487e-06, "loss": 1.6658, "step": 7 }, { "epoch": 0.018156028368794326, "grad_norm": 5.177608489990234, "learning_rate": 9.954128440366973e-06, "loss": 1.5814, "step": 8 }, { "epoch": 0.020425531914893616, "grad_norm": 3.236107110977173, "learning_rate": 9.931192660550459e-06, "loss": 1.4174, "step": 9 }, { "epoch": 0.02269503546099291, "grad_norm": 2.5157792568206787, "learning_rate": 9.908256880733946e-06, "loss": 1.4579, "step": 10 }, { "epoch": 0.0249645390070922, "grad_norm": 2.337372064590454, "learning_rate": 9.885321100917432e-06, "loss": 1.3153, "step": 11 }, { "epoch": 0.02723404255319149, "grad_norm": 2.264194965362549, "learning_rate": 9.862385321100918e-06, "loss": 1.5499, "step": 12 }, { "epoch": 0.02950354609929078, "grad_norm": 2.1040542125701904, "learning_rate": 9.839449541284404e-06, "loss": 1.4358, "step": 13 }, { "epoch": 0.03177304964539007, "grad_norm": 2.018862247467041, "learning_rate": 9.81651376146789e-06, "loss": 1.4913, "step": 14 }, { "epoch": 0.03404255319148936, "grad_norm": 1.7114828824996948, "learning_rate": 9.793577981651376e-06, "loss": 1.3369, "step": 15 }, { "epoch": 0.03631205673758865, "grad_norm": 1.6578619480133057, "learning_rate": 9.770642201834864e-06, "loss": 1.1885, "step": 16 }, { "epoch": 0.03858156028368794, "grad_norm": 1.8393357992172241, "learning_rate": 9.74770642201835e-06, "loss": 1.3145, "step": 17 }, { "epoch": 0.04085106382978723, "grad_norm": 1.855263352394104, "learning_rate": 9.724770642201836e-06, "loss": 1.3288, "step": 18 }, { "epoch": 0.04312056737588652, "grad_norm": 1.4408148527145386, "learning_rate": 9.701834862385322e-06, "loss": 1.2142, "step": 19 }, { "epoch": 0.04539007092198582, "grad_norm": 1.527726411819458, "learning_rate": 9.678899082568808e-06, "loss": 1.2233, "step": 20 }, { "epoch": 0.04765957446808511, "grad_norm": 1.6266558170318604, "learning_rate": 9.655963302752295e-06, "loss": 1.3116, "step": 21 }, { "epoch": 0.0499290780141844, "grad_norm": 1.4817768335342407, "learning_rate": 9.633027522935781e-06, "loss": 1.1593, "step": 22 }, { "epoch": 0.05219858156028369, "grad_norm": 1.4881550073623657, "learning_rate": 9.610091743119267e-06, "loss": 1.2051, "step": 23 }, { "epoch": 0.05446808510638298, "grad_norm": 1.577528476715088, "learning_rate": 9.587155963302753e-06, "loss": 1.2091, "step": 24 }, { "epoch": 0.05673758865248227, "grad_norm": 1.457054615020752, "learning_rate": 9.56422018348624e-06, "loss": 1.2113, "step": 25 }, { "epoch": 0.05900709219858156, "grad_norm": 1.5845608711242676, "learning_rate": 9.541284403669727e-06, "loss": 1.2154, "step": 26 }, { "epoch": 0.06127659574468085, "grad_norm": 1.4266366958618164, "learning_rate": 9.518348623853211e-06, "loss": 1.2865, "step": 27 }, { "epoch": 0.06354609929078014, "grad_norm": 1.6798540353775024, "learning_rate": 9.495412844036697e-06, "loss": 1.0629, "step": 28 }, { "epoch": 0.06581560283687943, "grad_norm": 1.5675240755081177, "learning_rate": 9.472477064220185e-06, "loss": 1.2149, "step": 29 }, { "epoch": 0.06808510638297872, "grad_norm": 1.5445024967193604, "learning_rate": 9.44954128440367e-06, "loss": 1.2659, "step": 30 }, { "epoch": 0.07035460992907801, "grad_norm": 1.602843165397644, "learning_rate": 9.426605504587157e-06, "loss": 1.0757, "step": 31 }, { "epoch": 0.0726241134751773, "grad_norm": 1.6502028703689575, "learning_rate": 9.403669724770643e-06, "loss": 1.3232, "step": 32 }, { "epoch": 0.0748936170212766, "grad_norm": 1.4741336107254028, "learning_rate": 9.380733944954129e-06, "loss": 1.2026, "step": 33 }, { "epoch": 0.07716312056737588, "grad_norm": 1.5695512294769287, "learning_rate": 9.357798165137616e-06, "loss": 1.129, "step": 34 }, { "epoch": 0.07943262411347518, "grad_norm": 1.5674344301223755, "learning_rate": 9.334862385321102e-06, "loss": 1.2214, "step": 35 }, { "epoch": 0.08170212765957446, "grad_norm": 1.6371891498565674, "learning_rate": 9.311926605504588e-06, "loss": 1.1249, "step": 36 }, { "epoch": 0.08397163120567376, "grad_norm": 1.496510624885559, "learning_rate": 9.288990825688074e-06, "loss": 1.0491, "step": 37 }, { "epoch": 0.08624113475177304, "grad_norm": 1.4194750785827637, "learning_rate": 9.26605504587156e-06, "loss": 1.0939, "step": 38 }, { "epoch": 0.08851063829787234, "grad_norm": 1.7404779195785522, "learning_rate": 9.243119266055046e-06, "loss": 1.0867, "step": 39 }, { "epoch": 0.09078014184397164, "grad_norm": 1.491525650024414, "learning_rate": 9.220183486238534e-06, "loss": 1.0534, "step": 40 }, { "epoch": 0.09304964539007092, "grad_norm": 2.243171215057373, "learning_rate": 9.19724770642202e-06, "loss": 1.2851, "step": 41 }, { "epoch": 0.09531914893617022, "grad_norm": 1.4284172058105469, "learning_rate": 9.174311926605506e-06, "loss": 1.1236, "step": 42 }, { "epoch": 0.0975886524822695, "grad_norm": 1.616500973701477, "learning_rate": 9.151376146788992e-06, "loss": 1.2548, "step": 43 }, { "epoch": 0.0998581560283688, "grad_norm": 1.4972879886627197, "learning_rate": 9.128440366972477e-06, "loss": 1.1649, "step": 44 }, { "epoch": 0.10212765957446808, "grad_norm": 1.306430459022522, "learning_rate": 9.105504587155965e-06, "loss": 1.1015, "step": 45 }, { "epoch": 0.10439716312056738, "grad_norm": 1.346713662147522, "learning_rate": 9.08256880733945e-06, "loss": 1.0399, "step": 46 }, { "epoch": 0.10666666666666667, "grad_norm": 1.351098656654358, "learning_rate": 9.059633027522935e-06, "loss": 1.1454, "step": 47 }, { "epoch": 0.10893617021276596, "grad_norm": 1.4924017190933228, "learning_rate": 9.036697247706423e-06, "loss": 1.1259, "step": 48 }, { "epoch": 0.11120567375886525, "grad_norm": 1.4457885026931763, "learning_rate": 9.013761467889909e-06, "loss": 1.2877, "step": 49 }, { "epoch": 0.11347517730496454, "grad_norm": 1.4125986099243164, "learning_rate": 8.990825688073395e-06, "loss": 1.101, "step": 50 }, { "epoch": 0.11574468085106383, "grad_norm": 1.5077935457229614, "learning_rate": 8.967889908256881e-06, "loss": 1.0646, "step": 51 }, { "epoch": 0.11801418439716312, "grad_norm": 1.4977812767028809, "learning_rate": 8.944954128440367e-06, "loss": 1.2349, "step": 52 }, { "epoch": 0.12028368794326241, "grad_norm": 1.423365831375122, "learning_rate": 8.922018348623855e-06, "loss": 1.1137, "step": 53 }, { "epoch": 0.1225531914893617, "grad_norm": 1.5771822929382324, "learning_rate": 8.89908256880734e-06, "loss": 1.1495, "step": 54 }, { "epoch": 0.12482269503546099, "grad_norm": 1.684470534324646, "learning_rate": 8.876146788990826e-06, "loss": 1.2508, "step": 55 }, { "epoch": 0.1270921985815603, "grad_norm": 1.455635666847229, "learning_rate": 8.853211009174312e-06, "loss": 1.1445, "step": 56 }, { "epoch": 0.12936170212765957, "grad_norm": 1.5448224544525146, "learning_rate": 8.830275229357798e-06, "loss": 1.1064, "step": 57 }, { "epoch": 0.13163120567375886, "grad_norm": 1.4774034023284912, "learning_rate": 8.807339449541286e-06, "loss": 1.2192, "step": 58 }, { "epoch": 0.13390070921985817, "grad_norm": 1.3867689371109009, "learning_rate": 8.784403669724772e-06, "loss": 1.0249, "step": 59 }, { "epoch": 0.13617021276595745, "grad_norm": 1.399766206741333, "learning_rate": 8.761467889908258e-06, "loss": 1.1511, "step": 60 }, { "epoch": 0.13843971631205673, "grad_norm": 1.4242483377456665, "learning_rate": 8.738532110091744e-06, "loss": 1.0874, "step": 61 }, { "epoch": 0.14070921985815601, "grad_norm": 1.5468575954437256, "learning_rate": 8.71559633027523e-06, "loss": 1.1651, "step": 62 }, { "epoch": 0.14297872340425533, "grad_norm": 1.6245957612991333, "learning_rate": 8.692660550458716e-06, "loss": 1.0723, "step": 63 }, { "epoch": 0.1452482269503546, "grad_norm": 1.6098276376724243, "learning_rate": 8.669724770642203e-06, "loss": 1.0325, "step": 64 }, { "epoch": 0.1475177304964539, "grad_norm": 1.5643788576126099, "learning_rate": 8.646788990825688e-06, "loss": 1.218, "step": 65 }, { "epoch": 0.1497872340425532, "grad_norm": 1.637283444404602, "learning_rate": 8.623853211009175e-06, "loss": 1.1349, "step": 66 }, { "epoch": 0.15205673758865249, "grad_norm": 1.5032382011413574, "learning_rate": 8.600917431192661e-06, "loss": 1.0963, "step": 67 }, { "epoch": 0.15432624113475177, "grad_norm": 1.4575449228286743, "learning_rate": 8.577981651376147e-06, "loss": 1.1248, "step": 68 }, { "epoch": 0.15659574468085105, "grad_norm": 1.5326515436172485, "learning_rate": 8.555045871559633e-06, "loss": 1.1902, "step": 69 }, { "epoch": 0.15886524822695036, "grad_norm": 1.6938763856887817, "learning_rate": 8.53211009174312e-06, "loss": 1.2707, "step": 70 }, { "epoch": 0.16113475177304964, "grad_norm": 1.5164247751235962, "learning_rate": 8.509174311926605e-06, "loss": 1.054, "step": 71 }, { "epoch": 0.16340425531914893, "grad_norm": 1.5911948680877686, "learning_rate": 8.486238532110093e-06, "loss": 1.1876, "step": 72 }, { "epoch": 0.16567375886524824, "grad_norm": 1.446104884147644, "learning_rate": 8.463302752293579e-06, "loss": 1.212, "step": 73 }, { "epoch": 0.16794326241134752, "grad_norm": 1.5896426439285278, "learning_rate": 8.440366972477065e-06, "loss": 1.2147, "step": 74 }, { "epoch": 0.1702127659574468, "grad_norm": 1.6771634817123413, "learning_rate": 8.41743119266055e-06, "loss": 1.1833, "step": 75 }, { "epoch": 0.1724822695035461, "grad_norm": 1.6042940616607666, "learning_rate": 8.394495412844037e-06, "loss": 1.0569, "step": 76 }, { "epoch": 0.1747517730496454, "grad_norm": 1.5487030744552612, "learning_rate": 8.371559633027524e-06, "loss": 1.1404, "step": 77 }, { "epoch": 0.17702127659574468, "grad_norm": 1.5248790979385376, "learning_rate": 8.34862385321101e-06, "loss": 1.1571, "step": 78 }, { "epoch": 0.17929078014184396, "grad_norm": 1.6195831298828125, "learning_rate": 8.325688073394496e-06, "loss": 1.1104, "step": 79 }, { "epoch": 0.18156028368794327, "grad_norm": 1.490044355392456, "learning_rate": 8.302752293577982e-06, "loss": 0.9797, "step": 80 }, { "epoch": 0.18382978723404256, "grad_norm": 1.7148139476776123, "learning_rate": 8.279816513761468e-06, "loss": 1.229, "step": 81 }, { "epoch": 0.18609929078014184, "grad_norm": 1.5580657720565796, "learning_rate": 8.256880733944956e-06, "loss": 1.1811, "step": 82 }, { "epoch": 0.18836879432624112, "grad_norm": 1.75330650806427, "learning_rate": 8.233944954128442e-06, "loss": 1.0723, "step": 83 }, { "epoch": 0.19063829787234043, "grad_norm": 1.3820202350616455, "learning_rate": 8.211009174311926e-06, "loss": 1.024, "step": 84 }, { "epoch": 0.19290780141843972, "grad_norm": 1.4940160512924194, "learning_rate": 8.188073394495414e-06, "loss": 1.0503, "step": 85 }, { "epoch": 0.195177304964539, "grad_norm": 1.4443671703338623, "learning_rate": 8.1651376146789e-06, "loss": 1.004, "step": 86 }, { "epoch": 0.1974468085106383, "grad_norm": 1.4839706420898438, "learning_rate": 8.142201834862386e-06, "loss": 0.9893, "step": 87 }, { "epoch": 0.1997163120567376, "grad_norm": 1.4716434478759766, "learning_rate": 8.119266055045872e-06, "loss": 1.1161, "step": 88 }, { "epoch": 0.20198581560283688, "grad_norm": 1.4870119094848633, "learning_rate": 8.096330275229358e-06, "loss": 1.123, "step": 89 }, { "epoch": 0.20425531914893616, "grad_norm": 1.5655701160430908, "learning_rate": 8.073394495412845e-06, "loss": 1.1761, "step": 90 }, { "epoch": 0.20652482269503547, "grad_norm": 1.6786651611328125, "learning_rate": 8.050458715596331e-06, "loss": 1.0348, "step": 91 }, { "epoch": 0.20879432624113475, "grad_norm": 1.6047208309173584, "learning_rate": 8.027522935779817e-06, "loss": 1.1222, "step": 92 }, { "epoch": 0.21106382978723404, "grad_norm": 1.5363961458206177, "learning_rate": 8.004587155963303e-06, "loss": 1.0585, "step": 93 }, { "epoch": 0.21333333333333335, "grad_norm": 1.6998924016952515, "learning_rate": 7.981651376146789e-06, "loss": 1.2009, "step": 94 }, { "epoch": 0.21560283687943263, "grad_norm": 1.477899432182312, "learning_rate": 7.958715596330275e-06, "loss": 1.1592, "step": 95 }, { "epoch": 0.2178723404255319, "grad_norm": 1.7220145463943481, "learning_rate": 7.935779816513763e-06, "loss": 1.2609, "step": 96 }, { "epoch": 0.2201418439716312, "grad_norm": 1.6309655904769897, "learning_rate": 7.912844036697249e-06, "loss": 1.147, "step": 97 }, { "epoch": 0.2224113475177305, "grad_norm": 1.5883212089538574, "learning_rate": 7.889908256880735e-06, "loss": 1.0504, "step": 98 }, { "epoch": 0.2246808510638298, "grad_norm": 1.5206390619277954, "learning_rate": 7.86697247706422e-06, "loss": 1.0353, "step": 99 }, { "epoch": 0.22695035460992907, "grad_norm": 1.8069106340408325, "learning_rate": 7.844036697247707e-06, "loss": 1.1064, "step": 100 }, { "epoch": 0.22921985815602836, "grad_norm": 1.6293996572494507, "learning_rate": 7.821100917431194e-06, "loss": 1.1901, "step": 101 }, { "epoch": 0.23148936170212767, "grad_norm": 1.6833168268203735, "learning_rate": 7.79816513761468e-06, "loss": 1.1451, "step": 102 }, { "epoch": 0.23375886524822695, "grad_norm": 2.0151827335357666, "learning_rate": 7.775229357798164e-06, "loss": 1.0832, "step": 103 }, { "epoch": 0.23602836879432623, "grad_norm": 1.703169822692871, "learning_rate": 7.752293577981652e-06, "loss": 1.1699, "step": 104 }, { "epoch": 0.23829787234042554, "grad_norm": 1.5609285831451416, "learning_rate": 7.729357798165138e-06, "loss": 1.0551, "step": 105 }, { "epoch": 0.24056737588652483, "grad_norm": 1.5917255878448486, "learning_rate": 7.706422018348626e-06, "loss": 1.088, "step": 106 }, { "epoch": 0.2428368794326241, "grad_norm": 1.5587153434753418, "learning_rate": 7.68348623853211e-06, "loss": 1.0641, "step": 107 }, { "epoch": 0.2451063829787234, "grad_norm": 1.6691441535949707, "learning_rate": 7.660550458715596e-06, "loss": 1.0458, "step": 108 }, { "epoch": 0.2473758865248227, "grad_norm": 1.4876048564910889, "learning_rate": 7.637614678899084e-06, "loss": 1.184, "step": 109 }, { "epoch": 0.24964539007092199, "grad_norm": 1.6346971988677979, "learning_rate": 7.6146788990825695e-06, "loss": 1.0117, "step": 110 }, { "epoch": 0.2519148936170213, "grad_norm": 1.4629358053207397, "learning_rate": 7.5917431192660555e-06, "loss": 1.0566, "step": 111 }, { "epoch": 0.2541843971631206, "grad_norm": 1.500614047050476, "learning_rate": 7.568807339449542e-06, "loss": 1.1359, "step": 112 }, { "epoch": 0.25645390070921986, "grad_norm": 1.5671252012252808, "learning_rate": 7.545871559633028e-06, "loss": 1.0902, "step": 113 }, { "epoch": 0.25872340425531914, "grad_norm": 1.6015598773956299, "learning_rate": 7.522935779816515e-06, "loss": 1.0625, "step": 114 }, { "epoch": 0.26099290780141843, "grad_norm": 1.5570940971374512, "learning_rate": 7.500000000000001e-06, "loss": 1.0408, "step": 115 }, { "epoch": 0.2632624113475177, "grad_norm": 1.6530826091766357, "learning_rate": 7.477064220183486e-06, "loss": 1.0104, "step": 116 }, { "epoch": 0.265531914893617, "grad_norm": 1.6257294416427612, "learning_rate": 7.454128440366973e-06, "loss": 1.0042, "step": 117 }, { "epoch": 0.26780141843971633, "grad_norm": 1.970604419708252, "learning_rate": 7.431192660550459e-06, "loss": 1.155, "step": 118 }, { "epoch": 0.2700709219858156, "grad_norm": 1.8237806558609009, "learning_rate": 7.408256880733946e-06, "loss": 1.1599, "step": 119 }, { "epoch": 0.2723404255319149, "grad_norm": 1.5585662126541138, "learning_rate": 7.385321100917432e-06, "loss": 1.0297, "step": 120 }, { "epoch": 0.2746099290780142, "grad_norm": 1.5332691669464111, "learning_rate": 7.362385321100918e-06, "loss": 1.0908, "step": 121 }, { "epoch": 0.27687943262411346, "grad_norm": 1.5327073335647583, "learning_rate": 7.3394495412844045e-06, "loss": 1.1447, "step": 122 }, { "epoch": 0.27914893617021275, "grad_norm": 1.6033738851547241, "learning_rate": 7.31651376146789e-06, "loss": 1.0242, "step": 123 }, { "epoch": 0.28141843971631203, "grad_norm": 1.6213641166687012, "learning_rate": 7.293577981651376e-06, "loss": 1.1236, "step": 124 }, { "epoch": 0.28368794326241137, "grad_norm": 1.5888553857803345, "learning_rate": 7.270642201834863e-06, "loss": 1.1741, "step": 125 }, { "epoch": 0.28595744680851065, "grad_norm": 1.5639172792434692, "learning_rate": 7.247706422018349e-06, "loss": 1.0677, "step": 126 }, { "epoch": 0.28822695035460993, "grad_norm": 1.6216630935668945, "learning_rate": 7.224770642201836e-06, "loss": 1.1811, "step": 127 }, { "epoch": 0.2904964539007092, "grad_norm": 1.6817898750305176, "learning_rate": 7.201834862385322e-06, "loss": 1.1972, "step": 128 }, { "epoch": 0.2927659574468085, "grad_norm": 1.9262802600860596, "learning_rate": 7.178899082568808e-06, "loss": 1.1935, "step": 129 }, { "epoch": 0.2950354609929078, "grad_norm": 1.6068954467773438, "learning_rate": 7.155963302752295e-06, "loss": 1.0263, "step": 130 }, { "epoch": 0.29730496453900707, "grad_norm": 1.5314372777938843, "learning_rate": 7.133027522935781e-06, "loss": 1.1062, "step": 131 }, { "epoch": 0.2995744680851064, "grad_norm": 1.4909676313400269, "learning_rate": 7.110091743119267e-06, "loss": 1.1434, "step": 132 }, { "epoch": 0.3018439716312057, "grad_norm": 1.8038368225097656, "learning_rate": 7.087155963302753e-06, "loss": 1.2193, "step": 133 }, { "epoch": 0.30411347517730497, "grad_norm": 1.5871021747589111, "learning_rate": 7.0642201834862385e-06, "loss": 0.9734, "step": 134 }, { "epoch": 0.30638297872340425, "grad_norm": 1.5635144710540771, "learning_rate": 7.041284403669726e-06, "loss": 1.04, "step": 135 }, { "epoch": 0.30865248226950354, "grad_norm": 1.57278311252594, "learning_rate": 7.018348623853211e-06, "loss": 1.1793, "step": 136 }, { "epoch": 0.3109219858156028, "grad_norm": 1.5725725889205933, "learning_rate": 6.995412844036697e-06, "loss": 1.0653, "step": 137 }, { "epoch": 0.3131914893617021, "grad_norm": 1.498573899269104, "learning_rate": 6.972477064220184e-06, "loss": 1.1278, "step": 138 }, { "epoch": 0.31546099290780144, "grad_norm": 1.647825002670288, "learning_rate": 6.94954128440367e-06, "loss": 1.1578, "step": 139 }, { "epoch": 0.3177304964539007, "grad_norm": 1.534072756767273, "learning_rate": 6.926605504587156e-06, "loss": 1.0307, "step": 140 }, { "epoch": 0.32, "grad_norm": 1.513083577156067, "learning_rate": 6.903669724770643e-06, "loss": 1.0293, "step": 141 }, { "epoch": 0.3222695035460993, "grad_norm": 1.4749670028686523, "learning_rate": 6.880733944954129e-06, "loss": 1.1083, "step": 142 }, { "epoch": 0.3245390070921986, "grad_norm": 1.583092451095581, "learning_rate": 6.8577981651376156e-06, "loss": 1.051, "step": 143 }, { "epoch": 0.32680851063829786, "grad_norm": 1.609663724899292, "learning_rate": 6.8348623853211015e-06, "loss": 1.0836, "step": 144 }, { "epoch": 0.32907801418439714, "grad_norm": 1.5559171438217163, "learning_rate": 6.8119266055045875e-06, "loss": 1.0763, "step": 145 }, { "epoch": 0.3313475177304965, "grad_norm": 1.57758367061615, "learning_rate": 6.788990825688074e-06, "loss": 1.1245, "step": 146 }, { "epoch": 0.33361702127659576, "grad_norm": 1.6211820840835571, "learning_rate": 6.76605504587156e-06, "loss": 1.0211, "step": 147 }, { "epoch": 0.33588652482269504, "grad_norm": 1.6207329034805298, "learning_rate": 6.743119266055046e-06, "loss": 1.0903, "step": 148 }, { "epoch": 0.3381560283687943, "grad_norm": 1.4234338998794556, "learning_rate": 6.720183486238533e-06, "loss": 1.0549, "step": 149 }, { "epoch": 0.3404255319148936, "grad_norm": 1.5573631525039673, "learning_rate": 6.697247706422019e-06, "loss": 1.2149, "step": 150 }, { "epoch": 0.3426950354609929, "grad_norm": 1.6138056516647339, "learning_rate": 6.674311926605506e-06, "loss": 1.1153, "step": 151 }, { "epoch": 0.3449645390070922, "grad_norm": 1.5717531442642212, "learning_rate": 6.651376146788992e-06, "loss": 1.1248, "step": 152 }, { "epoch": 0.3472340425531915, "grad_norm": 1.5182626247406006, "learning_rate": 6.628440366972477e-06, "loss": 1.0725, "step": 153 }, { "epoch": 0.3495035460992908, "grad_norm": 1.599070429801941, "learning_rate": 6.6055045871559645e-06, "loss": 1.0926, "step": 154 }, { "epoch": 0.3517730496453901, "grad_norm": 1.5615801811218262, "learning_rate": 6.58256880733945e-06, "loss": 1.1547, "step": 155 }, { "epoch": 0.35404255319148936, "grad_norm": 1.4162999391555786, "learning_rate": 6.559633027522936e-06, "loss": 1.0629, "step": 156 }, { "epoch": 0.35631205673758864, "grad_norm": 1.6145439147949219, "learning_rate": 6.536697247706422e-06, "loss": 1.2067, "step": 157 }, { "epoch": 0.35858156028368793, "grad_norm": 1.5748608112335205, "learning_rate": 6.513761467889908e-06, "loss": 0.9828, "step": 158 }, { "epoch": 0.3608510638297872, "grad_norm": 1.578722357749939, "learning_rate": 6.490825688073395e-06, "loss": 1.1281, "step": 159 }, { "epoch": 0.36312056737588655, "grad_norm": 1.7396999597549438, "learning_rate": 6.467889908256881e-06, "loss": 1.0204, "step": 160 }, { "epoch": 0.36539007092198583, "grad_norm": 1.6529046297073364, "learning_rate": 6.444954128440367e-06, "loss": 0.9384, "step": 161 }, { "epoch": 0.3676595744680851, "grad_norm": 1.6508899927139282, "learning_rate": 6.422018348623854e-06, "loss": 1.0395, "step": 162 }, { "epoch": 0.3699290780141844, "grad_norm": 1.753536581993103, "learning_rate": 6.39908256880734e-06, "loss": 1.0733, "step": 163 }, { "epoch": 0.3721985815602837, "grad_norm": 1.7516933679580688, "learning_rate": 6.376146788990826e-06, "loss": 1.0822, "step": 164 }, { "epoch": 0.37446808510638296, "grad_norm": 1.5380916595458984, "learning_rate": 6.353211009174313e-06, "loss": 1.0634, "step": 165 }, { "epoch": 0.37673758865248225, "grad_norm": 1.7386542558670044, "learning_rate": 6.330275229357799e-06, "loss": 1.129, "step": 166 }, { "epoch": 0.3790070921985816, "grad_norm": 1.6971700191497803, "learning_rate": 6.307339449541285e-06, "loss": 1.0893, "step": 167 }, { "epoch": 0.38127659574468087, "grad_norm": 1.7294853925704956, "learning_rate": 6.284403669724771e-06, "loss": 1.0438, "step": 168 }, { "epoch": 0.38354609929078015, "grad_norm": 1.67743718624115, "learning_rate": 6.261467889908257e-06, "loss": 0.9701, "step": 169 }, { "epoch": 0.38581560283687943, "grad_norm": 1.707750916481018, "learning_rate": 6.238532110091744e-06, "loss": 1.0753, "step": 170 }, { "epoch": 0.3880851063829787, "grad_norm": 1.727271556854248, "learning_rate": 6.21559633027523e-06, "loss": 1.055, "step": 171 }, { "epoch": 0.390354609929078, "grad_norm": 1.6818029880523682, "learning_rate": 6.192660550458715e-06, "loss": 1.0136, "step": 172 }, { "epoch": 0.3926241134751773, "grad_norm": 1.6080245971679688, "learning_rate": 6.169724770642203e-06, "loss": 0.9131, "step": 173 }, { "epoch": 0.3948936170212766, "grad_norm": 1.698134183883667, "learning_rate": 6.146788990825688e-06, "loss": 1.2139, "step": 174 }, { "epoch": 0.3971631205673759, "grad_norm": 1.5407640933990479, "learning_rate": 6.123853211009176e-06, "loss": 0.9525, "step": 175 }, { "epoch": 0.3994326241134752, "grad_norm": 1.7005316019058228, "learning_rate": 6.100917431192661e-06, "loss": 1.0543, "step": 176 }, { "epoch": 0.40170212765957447, "grad_norm": 1.600319504737854, "learning_rate": 6.077981651376147e-06, "loss": 1.1218, "step": 177 }, { "epoch": 0.40397163120567375, "grad_norm": 1.555154800415039, "learning_rate": 6.0550458715596335e-06, "loss": 1.147, "step": 178 }, { "epoch": 0.40624113475177304, "grad_norm": 1.5128672122955322, "learning_rate": 6.0321100917431195e-06, "loss": 1.0767, "step": 179 }, { "epoch": 0.4085106382978723, "grad_norm": 1.604812502861023, "learning_rate": 6.0091743119266054e-06, "loss": 1.0384, "step": 180 }, { "epoch": 0.41078014184397166, "grad_norm": 1.5982609987258911, "learning_rate": 5.986238532110092e-06, "loss": 1.0281, "step": 181 }, { "epoch": 0.41304964539007094, "grad_norm": 1.6095682382583618, "learning_rate": 5.963302752293578e-06, "loss": 1.0886, "step": 182 }, { "epoch": 0.4153191489361702, "grad_norm": 1.6036173105239868, "learning_rate": 5.940366972477065e-06, "loss": 0.9559, "step": 183 }, { "epoch": 0.4175886524822695, "grad_norm": 1.5238580703735352, "learning_rate": 5.917431192660551e-06, "loss": 1.0769, "step": 184 }, { "epoch": 0.4198581560283688, "grad_norm": 1.4887105226516724, "learning_rate": 5.894495412844037e-06, "loss": 1.0025, "step": 185 }, { "epoch": 0.4221276595744681, "grad_norm": 1.4986013174057007, "learning_rate": 5.871559633027524e-06, "loss": 1.0497, "step": 186 }, { "epoch": 0.42439716312056736, "grad_norm": 1.5539681911468506, "learning_rate": 5.84862385321101e-06, "loss": 1.0634, "step": 187 }, { "epoch": 0.4266666666666667, "grad_norm": 1.7040444612503052, "learning_rate": 5.825688073394496e-06, "loss": 1.0851, "step": 188 }, { "epoch": 0.428936170212766, "grad_norm": 1.6696319580078125, "learning_rate": 5.8027522935779825e-06, "loss": 1.1568, "step": 189 }, { "epoch": 0.43120567375886526, "grad_norm": 1.6318204402923584, "learning_rate": 5.7798165137614684e-06, "loss": 0.9509, "step": 190 }, { "epoch": 0.43347517730496454, "grad_norm": 1.5709612369537354, "learning_rate": 5.756880733944955e-06, "loss": 1.0372, "step": 191 }, { "epoch": 0.4357446808510638, "grad_norm": 1.5714880228042603, "learning_rate": 5.733944954128441e-06, "loss": 1.0148, "step": 192 }, { "epoch": 0.4380141843971631, "grad_norm": 1.915330171585083, "learning_rate": 5.711009174311926e-06, "loss": 1.1441, "step": 193 }, { "epoch": 0.4402836879432624, "grad_norm": 1.558813214302063, "learning_rate": 5.688073394495414e-06, "loss": 0.9939, "step": 194 }, { "epoch": 0.4425531914893617, "grad_norm": 1.6729793548583984, "learning_rate": 5.665137614678899e-06, "loss": 1.0155, "step": 195 }, { "epoch": 0.444822695035461, "grad_norm": 1.8084522485733032, "learning_rate": 5.642201834862385e-06, "loss": 1.0925, "step": 196 }, { "epoch": 0.4470921985815603, "grad_norm": 1.7066360712051392, "learning_rate": 5.619266055045872e-06, "loss": 0.9991, "step": 197 }, { "epoch": 0.4493617021276596, "grad_norm": 1.58521568775177, "learning_rate": 5.596330275229358e-06, "loss": 1.0692, "step": 198 }, { "epoch": 0.45163120567375886, "grad_norm": 1.6352282762527466, "learning_rate": 5.573394495412845e-06, "loss": 1.0555, "step": 199 }, { "epoch": 0.45390070921985815, "grad_norm": 1.5257892608642578, "learning_rate": 5.5504587155963306e-06, "loss": 1.0407, "step": 200 }, { "epoch": 0.45617021276595743, "grad_norm": 1.5424442291259766, "learning_rate": 5.5275229357798165e-06, "loss": 1.0557, "step": 201 }, { "epoch": 0.4584397163120567, "grad_norm": 1.6909080743789673, "learning_rate": 5.504587155963303e-06, "loss": 1.1206, "step": 202 }, { "epoch": 0.46070921985815605, "grad_norm": 1.558771014213562, "learning_rate": 5.481651376146789e-06, "loss": 1.0274, "step": 203 }, { "epoch": 0.46297872340425533, "grad_norm": 1.6251033544540405, "learning_rate": 5.458715596330275e-06, "loss": 0.9819, "step": 204 }, { "epoch": 0.4652482269503546, "grad_norm": 1.6708742380142212, "learning_rate": 5.435779816513762e-06, "loss": 0.957, "step": 205 }, { "epoch": 0.4675177304964539, "grad_norm": 1.5213267803192139, "learning_rate": 5.412844036697248e-06, "loss": 1.0377, "step": 206 }, { "epoch": 0.4697872340425532, "grad_norm": 1.5612300634384155, "learning_rate": 5.389908256880735e-06, "loss": 1.0517, "step": 207 }, { "epoch": 0.47205673758865246, "grad_norm": 1.6614094972610474, "learning_rate": 5.366972477064221e-06, "loss": 1.0941, "step": 208 }, { "epoch": 0.47432624113475175, "grad_norm": 1.5014389753341675, "learning_rate": 5.344036697247707e-06, "loss": 1.0369, "step": 209 }, { "epoch": 0.4765957446808511, "grad_norm": 1.5214993953704834, "learning_rate": 5.3211009174311936e-06, "loss": 1.2029, "step": 210 }, { "epoch": 0.47886524822695037, "grad_norm": 1.393906593322754, "learning_rate": 5.2981651376146795e-06, "loss": 1.0159, "step": 211 }, { "epoch": 0.48113475177304965, "grad_norm": 1.6334315538406372, "learning_rate": 5.275229357798165e-06, "loss": 1.1372, "step": 212 }, { "epoch": 0.48340425531914893, "grad_norm": 1.6396470069885254, "learning_rate": 5.252293577981652e-06, "loss": 1.1638, "step": 213 }, { "epoch": 0.4856737588652482, "grad_norm": 1.5385785102844238, "learning_rate": 5.229357798165137e-06, "loss": 1.069, "step": 214 }, { "epoch": 0.4879432624113475, "grad_norm": 1.8162378072738647, "learning_rate": 5.206422018348625e-06, "loss": 1.0653, "step": 215 }, { "epoch": 0.4902127659574468, "grad_norm": 1.6047035455703735, "learning_rate": 5.18348623853211e-06, "loss": 1.1112, "step": 216 }, { "epoch": 0.4924822695035461, "grad_norm": 1.6839237213134766, "learning_rate": 5.160550458715596e-06, "loss": 0.9423, "step": 217 }, { "epoch": 0.4947517730496454, "grad_norm": 1.5292307138442993, "learning_rate": 5.137614678899083e-06, "loss": 1.0857, "step": 218 }, { "epoch": 0.4970212765957447, "grad_norm": 1.5578291416168213, "learning_rate": 5.114678899082569e-06, "loss": 1.0809, "step": 219 }, { "epoch": 0.49929078014184397, "grad_norm": 1.696771264076233, "learning_rate": 5.091743119266055e-06, "loss": 0.9644, "step": 220 }, { "epoch": 0.5015602836879433, "grad_norm": 1.7158739566802979, "learning_rate": 5.068807339449542e-06, "loss": 1.0888, "step": 221 }, { "epoch": 0.5038297872340426, "grad_norm": 1.6630563735961914, "learning_rate": 5.045871559633028e-06, "loss": 1.119, "step": 222 }, { "epoch": 0.5060992907801418, "grad_norm": 1.5164653062820435, "learning_rate": 5.0229357798165144e-06, "loss": 0.947, "step": 223 }, { "epoch": 0.5083687943262412, "grad_norm": 1.7682493925094604, "learning_rate": 5e-06, "loss": 1.0935, "step": 224 }, { "epoch": 0.5106382978723404, "grad_norm": 1.5890684127807617, "learning_rate": 4.977064220183486e-06, "loss": 0.9592, "step": 225 }, { "epoch": 0.5129078014184397, "grad_norm": 1.6901733875274658, "learning_rate": 4.954128440366973e-06, "loss": 1.0507, "step": 226 }, { "epoch": 0.5151773049645391, "grad_norm": 1.6192798614501953, "learning_rate": 4.931192660550459e-06, "loss": 1.1498, "step": 227 }, { "epoch": 0.5174468085106383, "grad_norm": 1.588850736618042, "learning_rate": 4.908256880733945e-06, "loss": 1.0619, "step": 228 }, { "epoch": 0.5197163120567376, "grad_norm": 1.6203795671463013, "learning_rate": 4.885321100917432e-06, "loss": 1.1272, "step": 229 }, { "epoch": 0.5219858156028369, "grad_norm": 1.541406512260437, "learning_rate": 4.862385321100918e-06, "loss": 1.1506, "step": 230 }, { "epoch": 0.5242553191489362, "grad_norm": 1.7015891075134277, "learning_rate": 4.839449541284404e-06, "loss": 1.1172, "step": 231 }, { "epoch": 0.5265248226950354, "grad_norm": 1.5701123476028442, "learning_rate": 4.816513761467891e-06, "loss": 1.0434, "step": 232 }, { "epoch": 0.5287943262411348, "grad_norm": 1.570207953453064, "learning_rate": 4.793577981651377e-06, "loss": 1.0085, "step": 233 }, { "epoch": 0.531063829787234, "grad_norm": 1.5395921468734741, "learning_rate": 4.770642201834863e-06, "loss": 0.9542, "step": 234 }, { "epoch": 0.5333333333333333, "grad_norm": 1.590039849281311, "learning_rate": 4.7477064220183485e-06, "loss": 0.9871, "step": 235 }, { "epoch": 0.5356028368794327, "grad_norm": 1.8606112003326416, "learning_rate": 4.724770642201835e-06, "loss": 0.9985, "step": 236 }, { "epoch": 0.5378723404255319, "grad_norm": 1.997643232345581, "learning_rate": 4.701834862385321e-06, "loss": 1.1675, "step": 237 }, { "epoch": 0.5401418439716312, "grad_norm": 1.8751531839370728, "learning_rate": 4.678899082568808e-06, "loss": 1.2123, "step": 238 }, { "epoch": 0.5424113475177305, "grad_norm": 1.5691018104553223, "learning_rate": 4.655963302752294e-06, "loss": 1.0544, "step": 239 }, { "epoch": 0.5446808510638298, "grad_norm": 1.6681427955627441, "learning_rate": 4.63302752293578e-06, "loss": 1.1966, "step": 240 }, { "epoch": 0.546950354609929, "grad_norm": 1.539115071296692, "learning_rate": 4.610091743119267e-06, "loss": 1.0666, "step": 241 }, { "epoch": 0.5492198581560284, "grad_norm": 1.5979260206222534, "learning_rate": 4.587155963302753e-06, "loss": 1.0921, "step": 242 }, { "epoch": 0.5514893617021277, "grad_norm": 1.7149306535720825, "learning_rate": 4.564220183486239e-06, "loss": 1.0405, "step": 243 }, { "epoch": 0.5537588652482269, "grad_norm": 1.536405324935913, "learning_rate": 4.541284403669725e-06, "loss": 1.1371, "step": 244 }, { "epoch": 0.5560283687943263, "grad_norm": 1.6111186742782593, "learning_rate": 4.5183486238532115e-06, "loss": 1.1396, "step": 245 }, { "epoch": 0.5582978723404255, "grad_norm": 1.6651185750961304, "learning_rate": 4.4954128440366975e-06, "loss": 1.0105, "step": 246 }, { "epoch": 0.5605673758865248, "grad_norm": 1.6281050443649292, "learning_rate": 4.4724770642201834e-06, "loss": 0.9111, "step": 247 }, { "epoch": 0.5628368794326241, "grad_norm": 1.6061372756958008, "learning_rate": 4.44954128440367e-06, "loss": 0.9918, "step": 248 }, { "epoch": 0.5651063829787234, "grad_norm": 1.7501931190490723, "learning_rate": 4.426605504587156e-06, "loss": 1.0467, "step": 249 }, { "epoch": 0.5673758865248227, "grad_norm": 1.5185766220092773, "learning_rate": 4.403669724770643e-06, "loss": 1.037, "step": 250 }, { "epoch": 0.569645390070922, "grad_norm": 1.6851407289505005, "learning_rate": 4.380733944954129e-06, "loss": 1.1269, "step": 251 }, { "epoch": 0.5719148936170213, "grad_norm": 1.8020563125610352, "learning_rate": 4.357798165137615e-06, "loss": 1.0397, "step": 252 }, { "epoch": 0.5741843971631205, "grad_norm": 1.8341234922409058, "learning_rate": 4.334862385321102e-06, "loss": 1.1689, "step": 253 }, { "epoch": 0.5764539007092199, "grad_norm": 1.8023141622543335, "learning_rate": 4.311926605504588e-06, "loss": 1.1198, "step": 254 }, { "epoch": 0.5787234042553191, "grad_norm": 1.629441738128662, "learning_rate": 4.288990825688074e-06, "loss": 0.9871, "step": 255 }, { "epoch": 0.5809929078014184, "grad_norm": 1.8122279644012451, "learning_rate": 4.26605504587156e-06, "loss": 1.0451, "step": 256 }, { "epoch": 0.5832624113475178, "grad_norm": 1.7008877992630005, "learning_rate": 4.2431192660550464e-06, "loss": 1.111, "step": 257 }, { "epoch": 0.585531914893617, "grad_norm": 1.8434345722198486, "learning_rate": 4.220183486238532e-06, "loss": 0.9835, "step": 258 }, { "epoch": 0.5878014184397163, "grad_norm": 1.6210373640060425, "learning_rate": 4.197247706422018e-06, "loss": 1.0455, "step": 259 }, { "epoch": 0.5900709219858156, "grad_norm": 1.7073570489883423, "learning_rate": 4.174311926605505e-06, "loss": 1.085, "step": 260 }, { "epoch": 0.5923404255319149, "grad_norm": 1.662000060081482, "learning_rate": 4.151376146788991e-06, "loss": 1.1261, "step": 261 }, { "epoch": 0.5946099290780141, "grad_norm": 1.8483972549438477, "learning_rate": 4.128440366972478e-06, "loss": 1.1853, "step": 262 }, { "epoch": 0.5968794326241135, "grad_norm": 1.854033350944519, "learning_rate": 4.105504587155963e-06, "loss": 1.1494, "step": 263 }, { "epoch": 0.5991489361702128, "grad_norm": 1.6064186096191406, "learning_rate": 4.08256880733945e-06, "loss": 0.9857, "step": 264 }, { "epoch": 0.601418439716312, "grad_norm": 1.7795921564102173, "learning_rate": 4.059633027522936e-06, "loss": 1.0184, "step": 265 }, { "epoch": 0.6036879432624114, "grad_norm": 1.603488802909851, "learning_rate": 4.036697247706423e-06, "loss": 1.0285, "step": 266 }, { "epoch": 0.6059574468085106, "grad_norm": 1.8255984783172607, "learning_rate": 4.013761467889909e-06, "loss": 1.1503, "step": 267 }, { "epoch": 0.6082269503546099, "grad_norm": 1.6235878467559814, "learning_rate": 3.9908256880733945e-06, "loss": 1.112, "step": 268 }, { "epoch": 0.6104964539007092, "grad_norm": 1.7033151388168335, "learning_rate": 3.967889908256881e-06, "loss": 1.0216, "step": 269 }, { "epoch": 0.6127659574468085, "grad_norm": 1.682244896888733, "learning_rate": 3.944954128440367e-06, "loss": 1.2018, "step": 270 }, { "epoch": 0.6150354609929078, "grad_norm": 1.797347903251648, "learning_rate": 3.922018348623853e-06, "loss": 1.0863, "step": 271 }, { "epoch": 0.6173049645390071, "grad_norm": 1.7839646339416504, "learning_rate": 3.89908256880734e-06, "loss": 1.0316, "step": 272 }, { "epoch": 0.6195744680851064, "grad_norm": 1.9246529340744019, "learning_rate": 3.876146788990826e-06, "loss": 1.0426, "step": 273 }, { "epoch": 0.6218439716312056, "grad_norm": 1.7220736742019653, "learning_rate": 3.853211009174313e-06, "loss": 0.9674, "step": 274 }, { "epoch": 0.624113475177305, "grad_norm": 1.9574713706970215, "learning_rate": 3.830275229357798e-06, "loss": 1.0726, "step": 275 }, { "epoch": 0.6263829787234042, "grad_norm": 1.5741077661514282, "learning_rate": 3.8073394495412848e-06, "loss": 0.9143, "step": 276 }, { "epoch": 0.6286524822695035, "grad_norm": 1.591247797012329, "learning_rate": 3.784403669724771e-06, "loss": 1.0229, "step": 277 }, { "epoch": 0.6309219858156029, "grad_norm": 1.6965765953063965, "learning_rate": 3.7614678899082575e-06, "loss": 1.146, "step": 278 }, { "epoch": 0.6331914893617021, "grad_norm": 1.722831130027771, "learning_rate": 3.738532110091743e-06, "loss": 0.9957, "step": 279 }, { "epoch": 0.6354609929078014, "grad_norm": 1.6636874675750732, "learning_rate": 3.7155963302752295e-06, "loss": 1.2444, "step": 280 }, { "epoch": 0.6377304964539007, "grad_norm": 1.565240502357483, "learning_rate": 3.692660550458716e-06, "loss": 1.163, "step": 281 }, { "epoch": 0.64, "grad_norm": 1.7077933549880981, "learning_rate": 3.6697247706422022e-06, "loss": 1.0395, "step": 282 }, { "epoch": 0.6422695035460992, "grad_norm": 1.6656558513641357, "learning_rate": 3.646788990825688e-06, "loss": 0.952, "step": 283 }, { "epoch": 0.6445390070921986, "grad_norm": 1.708008885383606, "learning_rate": 3.6238532110091746e-06, "loss": 1.0705, "step": 284 }, { "epoch": 0.6468085106382979, "grad_norm": 1.699053406715393, "learning_rate": 3.600917431192661e-06, "loss": 1.1144, "step": 285 }, { "epoch": 0.6490780141843971, "grad_norm": 1.7110413312911987, "learning_rate": 3.5779816513761473e-06, "loss": 1.0406, "step": 286 }, { "epoch": 0.6513475177304965, "grad_norm": 1.6920559406280518, "learning_rate": 3.5550458715596333e-06, "loss": 0.9729, "step": 287 }, { "epoch": 0.6536170212765957, "grad_norm": 1.6601946353912354, "learning_rate": 3.5321100917431193e-06, "loss": 1.0858, "step": 288 }, { "epoch": 0.655886524822695, "grad_norm": 1.5750612020492554, "learning_rate": 3.5091743119266056e-06, "loss": 1.024, "step": 289 }, { "epoch": 0.6581560283687943, "grad_norm": 1.8492498397827148, "learning_rate": 3.486238532110092e-06, "loss": 1.1251, "step": 290 }, { "epoch": 0.6604255319148936, "grad_norm": 1.8008328676223755, "learning_rate": 3.463302752293578e-06, "loss": 1.0894, "step": 291 }, { "epoch": 0.662695035460993, "grad_norm": 1.665724754333496, "learning_rate": 3.4403669724770644e-06, "loss": 1.1039, "step": 292 }, { "epoch": 0.6649645390070922, "grad_norm": 1.6908433437347412, "learning_rate": 3.4174311926605508e-06, "loss": 1.0926, "step": 293 }, { "epoch": 0.6672340425531915, "grad_norm": 1.5396888256072998, "learning_rate": 3.394495412844037e-06, "loss": 1.0527, "step": 294 }, { "epoch": 0.6695035460992907, "grad_norm": 1.7278677225112915, "learning_rate": 3.371559633027523e-06, "loss": 1.127, "step": 295 }, { "epoch": 0.6717730496453901, "grad_norm": 1.5661567449569702, "learning_rate": 3.3486238532110095e-06, "loss": 1.0045, "step": 296 }, { "epoch": 0.6740425531914893, "grad_norm": 1.6483219861984253, "learning_rate": 3.325688073394496e-06, "loss": 1.1302, "step": 297 }, { "epoch": 0.6763120567375887, "grad_norm": 1.6740609407424927, "learning_rate": 3.3027522935779823e-06, "loss": 1.029, "step": 298 }, { "epoch": 0.678581560283688, "grad_norm": 1.7330656051635742, "learning_rate": 3.279816513761468e-06, "loss": 1.134, "step": 299 }, { "epoch": 0.6808510638297872, "grad_norm": 1.7417395114898682, "learning_rate": 3.256880733944954e-06, "loss": 1.057, "step": 300 }, { "epoch": 0.6831205673758866, "grad_norm": 1.695885181427002, "learning_rate": 3.2339449541284406e-06, "loss": 1.1331, "step": 301 }, { "epoch": 0.6853900709219858, "grad_norm": 1.7053548097610474, "learning_rate": 3.211009174311927e-06, "loss": 1.1068, "step": 302 }, { "epoch": 0.6876595744680851, "grad_norm": 1.604985237121582, "learning_rate": 3.188073394495413e-06, "loss": 1.0677, "step": 303 }, { "epoch": 0.6899290780141843, "grad_norm": 1.7643754482269287, "learning_rate": 3.1651376146788993e-06, "loss": 1.0889, "step": 304 }, { "epoch": 0.6921985815602837, "grad_norm": 1.5543439388275146, "learning_rate": 3.1422018348623857e-06, "loss": 1.1212, "step": 305 }, { "epoch": 0.694468085106383, "grad_norm": 1.6665397882461548, "learning_rate": 3.119266055045872e-06, "loss": 1.0056, "step": 306 }, { "epoch": 0.6967375886524823, "grad_norm": 1.603415846824646, "learning_rate": 3.0963302752293576e-06, "loss": 1.0604, "step": 307 }, { "epoch": 0.6990070921985816, "grad_norm": 2.050597906112671, "learning_rate": 3.073394495412844e-06, "loss": 1.062, "step": 308 }, { "epoch": 0.7012765957446808, "grad_norm": 1.8686933517456055, "learning_rate": 3.0504587155963304e-06, "loss": 0.9887, "step": 309 }, { "epoch": 0.7035460992907802, "grad_norm": 1.6227269172668457, "learning_rate": 3.0275229357798168e-06, "loss": 1.1606, "step": 310 }, { "epoch": 0.7058156028368794, "grad_norm": 1.7240091562271118, "learning_rate": 3.0045871559633027e-06, "loss": 1.1218, "step": 311 }, { "epoch": 0.7080851063829787, "grad_norm": 1.6275955438613892, "learning_rate": 2.981651376146789e-06, "loss": 0.9259, "step": 312 }, { "epoch": 0.7103546099290781, "grad_norm": 1.6439838409423828, "learning_rate": 2.9587155963302755e-06, "loss": 1.0352, "step": 313 }, { "epoch": 0.7126241134751773, "grad_norm": 1.7130757570266724, "learning_rate": 2.935779816513762e-06, "loss": 0.9703, "step": 314 }, { "epoch": 0.7148936170212766, "grad_norm": 1.7425600290298462, "learning_rate": 2.912844036697248e-06, "loss": 0.9685, "step": 315 }, { "epoch": 0.7171631205673759, "grad_norm": 1.8085887432098389, "learning_rate": 2.8899082568807342e-06, "loss": 1.1296, "step": 316 }, { "epoch": 0.7194326241134752, "grad_norm": 1.9008709192276, "learning_rate": 2.8669724770642206e-06, "loss": 1.0965, "step": 317 }, { "epoch": 0.7217021276595744, "grad_norm": 1.7641181945800781, "learning_rate": 2.844036697247707e-06, "loss": 1.0296, "step": 318 }, { "epoch": 0.7239716312056738, "grad_norm": 1.7710267305374146, "learning_rate": 2.8211009174311925e-06, "loss": 1.0355, "step": 319 }, { "epoch": 0.7262411347517731, "grad_norm": 1.7887316942214966, "learning_rate": 2.798165137614679e-06, "loss": 1.1746, "step": 320 }, { "epoch": 0.7285106382978723, "grad_norm": 1.7020350694656372, "learning_rate": 2.7752293577981653e-06, "loss": 1.003, "step": 321 }, { "epoch": 0.7307801418439717, "grad_norm": 1.8337253332138062, "learning_rate": 2.7522935779816517e-06, "loss": 1.0978, "step": 322 }, { "epoch": 0.7330496453900709, "grad_norm": 2.010838508605957, "learning_rate": 2.7293577981651376e-06, "loss": 1.103, "step": 323 }, { "epoch": 0.7353191489361702, "grad_norm": 1.6087417602539062, "learning_rate": 2.706422018348624e-06, "loss": 1.0024, "step": 324 }, { "epoch": 0.7375886524822695, "grad_norm": 1.6555931568145752, "learning_rate": 2.6834862385321104e-06, "loss": 1.0315, "step": 325 }, { "epoch": 0.7398581560283688, "grad_norm": 1.7955565452575684, "learning_rate": 2.6605504587155968e-06, "loss": 1.0421, "step": 326 }, { "epoch": 0.7421276595744681, "grad_norm": 1.6308382749557495, "learning_rate": 2.6376146788990823e-06, "loss": 1.1327, "step": 327 }, { "epoch": 0.7443971631205674, "grad_norm": 1.589514970779419, "learning_rate": 2.6146788990825687e-06, "loss": 1.1008, "step": 328 }, { "epoch": 0.7466666666666667, "grad_norm": 1.6569627523422241, "learning_rate": 2.591743119266055e-06, "loss": 1.1852, "step": 329 }, { "epoch": 0.7489361702127659, "grad_norm": 1.4999598264694214, "learning_rate": 2.5688073394495415e-06, "loss": 1.0484, "step": 330 }, { "epoch": 0.7512056737588653, "grad_norm": 1.5661509037017822, "learning_rate": 2.5458715596330274e-06, "loss": 1.0462, "step": 331 }, { "epoch": 0.7534751773049645, "grad_norm": 1.6866968870162964, "learning_rate": 2.522935779816514e-06, "loss": 1.0665, "step": 332 }, { "epoch": 0.7557446808510638, "grad_norm": 1.6729196310043335, "learning_rate": 2.5e-06, "loss": 0.9569, "step": 333 }, { "epoch": 0.7580141843971632, "grad_norm": 1.593554973602295, "learning_rate": 2.4770642201834866e-06, "loss": 1.0687, "step": 334 }, { "epoch": 0.7602836879432624, "grad_norm": 1.666972279548645, "learning_rate": 2.4541284403669725e-06, "loss": 1.0723, "step": 335 }, { "epoch": 0.7625531914893617, "grad_norm": 1.648990511894226, "learning_rate": 2.431192660550459e-06, "loss": 1.0022, "step": 336 }, { "epoch": 0.764822695035461, "grad_norm": 1.7422493696212769, "learning_rate": 2.4082568807339453e-06, "loss": 1.0013, "step": 337 }, { "epoch": 0.7670921985815603, "grad_norm": 1.751423954963684, "learning_rate": 2.3853211009174317e-06, "loss": 1.0718, "step": 338 }, { "epoch": 0.7693617021276595, "grad_norm": 1.6420936584472656, "learning_rate": 2.3623853211009177e-06, "loss": 1.0777, "step": 339 }, { "epoch": 0.7716312056737589, "grad_norm": 1.670432448387146, "learning_rate": 2.339449541284404e-06, "loss": 1.1626, "step": 340 }, { "epoch": 0.7739007092198582, "grad_norm": 1.5174460411071777, "learning_rate": 2.31651376146789e-06, "loss": 0.932, "step": 341 }, { "epoch": 0.7761702127659574, "grad_norm": 1.8283395767211914, "learning_rate": 2.2935779816513764e-06, "loss": 0.9368, "step": 342 }, { "epoch": 0.7784397163120568, "grad_norm": 1.6187958717346191, "learning_rate": 2.2706422018348624e-06, "loss": 1.1562, "step": 343 }, { "epoch": 0.780709219858156, "grad_norm": 1.7197251319885254, "learning_rate": 2.2477064220183487e-06, "loss": 1.0161, "step": 344 }, { "epoch": 0.7829787234042553, "grad_norm": 1.7202699184417725, "learning_rate": 2.224770642201835e-06, "loss": 0.9935, "step": 345 }, { "epoch": 0.7852482269503546, "grad_norm": 1.698126196861267, "learning_rate": 2.2018348623853215e-06, "loss": 1.0308, "step": 346 }, { "epoch": 0.7875177304964539, "grad_norm": 1.722468376159668, "learning_rate": 2.1788990825688075e-06, "loss": 1.1493, "step": 347 }, { "epoch": 0.7897872340425532, "grad_norm": 1.8182165622711182, "learning_rate": 2.155963302752294e-06, "loss": 1.1613, "step": 348 }, { "epoch": 0.7920567375886525, "grad_norm": 1.7522850036621094, "learning_rate": 2.13302752293578e-06, "loss": 0.9921, "step": 349 }, { "epoch": 0.7943262411347518, "grad_norm": 1.640934944152832, "learning_rate": 2.110091743119266e-06, "loss": 1.0495, "step": 350 }, { "epoch": 0.796595744680851, "grad_norm": 1.9130035638809204, "learning_rate": 2.0871559633027526e-06, "loss": 1.0809, "step": 351 }, { "epoch": 0.7988652482269504, "grad_norm": 1.7266210317611694, "learning_rate": 2.064220183486239e-06, "loss": 1.027, "step": 352 }, { "epoch": 0.8011347517730496, "grad_norm": 1.6870225667953491, "learning_rate": 2.041284403669725e-06, "loss": 1.0931, "step": 353 }, { "epoch": 0.8034042553191489, "grad_norm": 1.6710115671157837, "learning_rate": 2.0183486238532113e-06, "loss": 1.0479, "step": 354 }, { "epoch": 0.8056737588652483, "grad_norm": 1.7462962865829468, "learning_rate": 1.9954128440366973e-06, "loss": 1.0839, "step": 355 }, { "epoch": 0.8079432624113475, "grad_norm": 1.6509385108947754, "learning_rate": 1.9724770642201837e-06, "loss": 1.0395, "step": 356 }, { "epoch": 0.8102127659574468, "grad_norm": 1.6627336740493774, "learning_rate": 1.94954128440367e-06, "loss": 0.9808, "step": 357 }, { "epoch": 0.8124822695035461, "grad_norm": 1.5818833112716675, "learning_rate": 1.9266055045871564e-06, "loss": 1.0055, "step": 358 }, { "epoch": 0.8147517730496454, "grad_norm": 1.7693796157836914, "learning_rate": 1.9036697247706424e-06, "loss": 1.1375, "step": 359 }, { "epoch": 0.8170212765957446, "grad_norm": 1.6578178405761719, "learning_rate": 1.8807339449541288e-06, "loss": 1.0091, "step": 360 }, { "epoch": 0.819290780141844, "grad_norm": 1.5661290884017944, "learning_rate": 1.8577981651376147e-06, "loss": 0.9656, "step": 361 }, { "epoch": 0.8215602836879433, "grad_norm": 1.6924868822097778, "learning_rate": 1.8348623853211011e-06, "loss": 1.1001, "step": 362 }, { "epoch": 0.8238297872340425, "grad_norm": 1.7331774234771729, "learning_rate": 1.8119266055045873e-06, "loss": 1.0653, "step": 363 }, { "epoch": 0.8260992907801419, "grad_norm": 1.6839802265167236, "learning_rate": 1.7889908256880737e-06, "loss": 1.1069, "step": 364 }, { "epoch": 0.8283687943262411, "grad_norm": 1.737117052078247, "learning_rate": 1.7660550458715596e-06, "loss": 1.0673, "step": 365 }, { "epoch": 0.8306382978723404, "grad_norm": 1.6333673000335693, "learning_rate": 1.743119266055046e-06, "loss": 1.0625, "step": 366 }, { "epoch": 0.8329078014184397, "grad_norm": 1.7048739194869995, "learning_rate": 1.7201834862385322e-06, "loss": 1.0641, "step": 367 }, { "epoch": 0.835177304964539, "grad_norm": 1.739282250404358, "learning_rate": 1.6972477064220186e-06, "loss": 1.0161, "step": 368 }, { "epoch": 0.8374468085106384, "grad_norm": 1.9002472162246704, "learning_rate": 1.6743119266055047e-06, "loss": 1.0607, "step": 369 }, { "epoch": 0.8397163120567376, "grad_norm": 1.7066599130630493, "learning_rate": 1.6513761467889911e-06, "loss": 1.121, "step": 370 }, { "epoch": 0.8419858156028369, "grad_norm": 1.6974424123764038, "learning_rate": 1.628440366972477e-06, "loss": 1.0431, "step": 371 }, { "epoch": 0.8442553191489361, "grad_norm": 1.8257323503494263, "learning_rate": 1.6055045871559635e-06, "loss": 1.0529, "step": 372 }, { "epoch": 0.8465248226950355, "grad_norm": 1.732797622680664, "learning_rate": 1.5825688073394496e-06, "loss": 1.1343, "step": 373 }, { "epoch": 0.8487943262411347, "grad_norm": 3.654939651489258, "learning_rate": 1.559633027522936e-06, "loss": 1.1082, "step": 374 }, { "epoch": 0.851063829787234, "grad_norm": 1.7586781978607178, "learning_rate": 1.536697247706422e-06, "loss": 1.0238, "step": 375 }, { "epoch": 0.8533333333333334, "grad_norm": 1.6385191679000854, "learning_rate": 1.5137614678899084e-06, "loss": 1.1211, "step": 376 }, { "epoch": 0.8556028368794326, "grad_norm": 1.568895936012268, "learning_rate": 1.4908256880733945e-06, "loss": 1.1041, "step": 377 }, { "epoch": 0.857872340425532, "grad_norm": 1.7413898706436157, "learning_rate": 1.467889908256881e-06, "loss": 0.9638, "step": 378 }, { "epoch": 0.8601418439716312, "grad_norm": 1.689238429069519, "learning_rate": 1.4449541284403671e-06, "loss": 1.088, "step": 379 }, { "epoch": 0.8624113475177305, "grad_norm": 1.6632860898971558, "learning_rate": 1.4220183486238535e-06, "loss": 1.121, "step": 380 }, { "epoch": 0.8646808510638297, "grad_norm": 1.727305293083191, "learning_rate": 1.3990825688073395e-06, "loss": 1.1057, "step": 381 }, { "epoch": 0.8669503546099291, "grad_norm": 1.753532886505127, "learning_rate": 1.3761467889908258e-06, "loss": 1.1023, "step": 382 }, { "epoch": 0.8692198581560284, "grad_norm": 1.675025224685669, "learning_rate": 1.353211009174312e-06, "loss": 1.0696, "step": 383 }, { "epoch": 0.8714893617021277, "grad_norm": 1.6489957571029663, "learning_rate": 1.3302752293577984e-06, "loss": 0.9411, "step": 384 }, { "epoch": 0.873758865248227, "grad_norm": 1.688939094543457, "learning_rate": 1.3073394495412844e-06, "loss": 1.0338, "step": 385 }, { "epoch": 0.8760283687943262, "grad_norm": 1.6969425678253174, "learning_rate": 1.2844036697247707e-06, "loss": 1.0284, "step": 386 }, { "epoch": 0.8782978723404256, "grad_norm": 1.7366392612457275, "learning_rate": 1.261467889908257e-06, "loss": 1.0304, "step": 387 }, { "epoch": 0.8805673758865248, "grad_norm": 1.656225323677063, "learning_rate": 1.2385321100917433e-06, "loss": 1.0259, "step": 388 }, { "epoch": 0.8828368794326241, "grad_norm": 1.6807879209518433, "learning_rate": 1.2155963302752295e-06, "loss": 1.0785, "step": 389 }, { "epoch": 0.8851063829787233, "grad_norm": 1.6813548803329468, "learning_rate": 1.1926605504587159e-06, "loss": 1.0107, "step": 390 }, { "epoch": 0.8873758865248227, "grad_norm": 1.8428771495819092, "learning_rate": 1.169724770642202e-06, "loss": 0.9818, "step": 391 }, { "epoch": 0.889645390070922, "grad_norm": 1.603624701499939, "learning_rate": 1.1467889908256882e-06, "loss": 0.9674, "step": 392 }, { "epoch": 0.8919148936170213, "grad_norm": 1.6203340291976929, "learning_rate": 1.1238532110091744e-06, "loss": 0.9457, "step": 393 }, { "epoch": 0.8941843971631206, "grad_norm": 1.7495254278182983, "learning_rate": 1.1009174311926608e-06, "loss": 1.0487, "step": 394 }, { "epoch": 0.8964539007092198, "grad_norm": 1.7385809421539307, "learning_rate": 1.077981651376147e-06, "loss": 1.0827, "step": 395 }, { "epoch": 0.8987234042553192, "grad_norm": 1.6907747983932495, "learning_rate": 1.055045871559633e-06, "loss": 1.0467, "step": 396 }, { "epoch": 0.9009929078014184, "grad_norm": 1.6336034536361694, "learning_rate": 1.0321100917431195e-06, "loss": 1.0679, "step": 397 }, { "epoch": 0.9032624113475177, "grad_norm": 1.7320250272750854, "learning_rate": 1.0091743119266057e-06, "loss": 1.1433, "step": 398 }, { "epoch": 0.9055319148936171, "grad_norm": 1.635118842124939, "learning_rate": 9.862385321100918e-07, "loss": 1.0263, "step": 399 }, { "epoch": 0.9078014184397163, "grad_norm": 1.6573808193206787, "learning_rate": 9.633027522935782e-07, "loss": 0.8933, "step": 400 }, { "epoch": 0.9100709219858156, "grad_norm": 1.804376482963562, "learning_rate": 9.403669724770644e-07, "loss": 1.0312, "step": 401 }, { "epoch": 0.9123404255319149, "grad_norm": 1.7704100608825684, "learning_rate": 9.174311926605506e-07, "loss": 1.0107, "step": 402 }, { "epoch": 0.9146099290780142, "grad_norm": 1.6957616806030273, "learning_rate": 8.944954128440368e-07, "loss": 1.0224, "step": 403 }, { "epoch": 0.9168794326241134, "grad_norm": 1.7063379287719727, "learning_rate": 8.71559633027523e-07, "loss": 1.1237, "step": 404 }, { "epoch": 0.9191489361702128, "grad_norm": 1.806520700454712, "learning_rate": 8.486238532110093e-07, "loss": 0.9698, "step": 405 }, { "epoch": 0.9214184397163121, "grad_norm": 1.5992575883865356, "learning_rate": 8.256880733944956e-07, "loss": 1.0746, "step": 406 }, { "epoch": 0.9236879432624113, "grad_norm": 1.6610678434371948, "learning_rate": 8.027522935779817e-07, "loss": 1.0988, "step": 407 }, { "epoch": 0.9259574468085107, "grad_norm": 1.9969687461853027, "learning_rate": 7.79816513761468e-07, "loss": 1.0576, "step": 408 }, { "epoch": 0.9282269503546099, "grad_norm": 1.7739843130111694, "learning_rate": 7.568807339449542e-07, "loss": 1.0703, "step": 409 }, { "epoch": 0.9304964539007092, "grad_norm": 1.7842634916305542, "learning_rate": 7.339449541284405e-07, "loss": 1.0641, "step": 410 }, { "epoch": 0.9327659574468085, "grad_norm": 1.7711912393569946, "learning_rate": 7.110091743119267e-07, "loss": 1.0288, "step": 411 }, { "epoch": 0.9350354609929078, "grad_norm": 1.7387950420379639, "learning_rate": 6.880733944954129e-07, "loss": 1.0179, "step": 412 }, { "epoch": 0.9373049645390071, "grad_norm": 1.64360511302948, "learning_rate": 6.651376146788992e-07, "loss": 1.0999, "step": 413 }, { "epoch": 0.9395744680851064, "grad_norm": 1.7573128938674927, "learning_rate": 6.422018348623854e-07, "loss": 1.0628, "step": 414 }, { "epoch": 0.9418439716312057, "grad_norm": 1.5932070016860962, "learning_rate": 6.192660550458716e-07, "loss": 1.0097, "step": 415 }, { "epoch": 0.9441134751773049, "grad_norm": 1.6802014112472534, "learning_rate": 5.963302752293579e-07, "loss": 1.0508, "step": 416 }, { "epoch": 0.9463829787234043, "grad_norm": 1.6761120557785034, "learning_rate": 5.733944954128441e-07, "loss": 0.9869, "step": 417 }, { "epoch": 0.9486524822695035, "grad_norm": 1.754440188407898, "learning_rate": 5.504587155963304e-07, "loss": 1.0132, "step": 418 }, { "epoch": 0.9509219858156028, "grad_norm": 1.697351336479187, "learning_rate": 5.275229357798165e-07, "loss": 1.0503, "step": 419 }, { "epoch": 0.9531914893617022, "grad_norm": 1.6293652057647705, "learning_rate": 5.045871559633028e-07, "loss": 1.0329, "step": 420 }, { "epoch": 0.9554609929078014, "grad_norm": 1.6385964155197144, "learning_rate": 4.816513761467891e-07, "loss": 1.0478, "step": 421 }, { "epoch": 0.9577304964539007, "grad_norm": 1.7059550285339355, "learning_rate": 4.587155963302753e-07, "loss": 1.1713, "step": 422 }, { "epoch": 0.96, "grad_norm": 1.5657905340194702, "learning_rate": 4.357798165137615e-07, "loss": 0.9577, "step": 423 }, { "epoch": 0.9622695035460993, "grad_norm": 1.6070735454559326, "learning_rate": 4.128440366972478e-07, "loss": 0.98, "step": 424 }, { "epoch": 0.9645390070921985, "grad_norm": 1.8088176250457764, "learning_rate": 3.89908256880734e-07, "loss": 1.1138, "step": 425 }, { "epoch": 0.9668085106382979, "grad_norm": 1.6910450458526611, "learning_rate": 3.6697247706422023e-07, "loss": 1.035, "step": 426 }, { "epoch": 0.9690780141843972, "grad_norm": 1.6391150951385498, "learning_rate": 3.4403669724770646e-07, "loss": 1.0474, "step": 427 }, { "epoch": 0.9713475177304964, "grad_norm": 1.6457332372665405, "learning_rate": 3.211009174311927e-07, "loss": 0.9792, "step": 428 }, { "epoch": 0.9736170212765958, "grad_norm": 1.6799724102020264, "learning_rate": 2.9816513761467896e-07, "loss": 1.166, "step": 429 }, { "epoch": 0.975886524822695, "grad_norm": 1.6824805736541748, "learning_rate": 2.752293577981652e-07, "loss": 1.0724, "step": 430 }, { "epoch": 0.9781560283687943, "grad_norm": 1.6258994340896606, "learning_rate": 2.522935779816514e-07, "loss": 1.1252, "step": 431 }, { "epoch": 0.9804255319148936, "grad_norm": 1.7700878381729126, "learning_rate": 2.2935779816513764e-07, "loss": 1.0167, "step": 432 }, { "epoch": 0.9826950354609929, "grad_norm": 1.7391152381896973, "learning_rate": 2.064220183486239e-07, "loss": 1.0563, "step": 433 }, { "epoch": 0.9849645390070922, "grad_norm": 1.6474604606628418, "learning_rate": 1.8348623853211012e-07, "loss": 0.9784, "step": 434 }, { "epoch": 0.9872340425531915, "grad_norm": 1.5483592748641968, "learning_rate": 1.6055045871559634e-07, "loss": 1.0227, "step": 435 }, { "epoch": 0.9895035460992908, "grad_norm": 1.865318775177002, "learning_rate": 1.376146788990826e-07, "loss": 1.1436, "step": 436 }, { "epoch": 0.99177304964539, "grad_norm": 1.7144179344177246, "learning_rate": 1.1467889908256882e-07, "loss": 1.0132, "step": 437 }, { "epoch": 0.9940425531914894, "grad_norm": 1.7456868886947632, "learning_rate": 9.174311926605506e-08, "loss": 1.1407, "step": 438 }, { "epoch": 0.9963120567375886, "grad_norm": 1.6428983211517334, "learning_rate": 6.88073394495413e-08, "loss": 0.9075, "step": 439 }, { "epoch": 0.9985815602836879, "grad_norm": 1.7114496231079102, "learning_rate": 4.587155963302753e-08, "loss": 0.9876, "step": 440 }, { "epoch": 1.0, "grad_norm": 2.3762407302856445, "learning_rate": 2.2935779816513765e-08, "loss": 1.1071, "step": 441 } ], "logging_steps": 1, "max_steps": 441, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.2130667855720653e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }