{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 933, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003215434083601286, "grad_norm": 28.06913370740238, "learning_rate": 0.0, "loss": 2.6452956199645996, "step": 1 }, { "epoch": 0.006430868167202572, "grad_norm": 48.39869965639885, "learning_rate": 1.0638297872340426e-07, "loss": 4.55789852142334, "step": 2 }, { "epoch": 0.00964630225080386, "grad_norm": 49.69301124062599, "learning_rate": 2.1276595744680852e-07, "loss": 4.399077415466309, "step": 3 }, { "epoch": 0.012861736334405145, "grad_norm": 41.69483295374549, "learning_rate": 3.1914893617021275e-07, "loss": 3.8412859439849854, "step": 4 }, { "epoch": 0.01607717041800643, "grad_norm": 38.19554788922322, "learning_rate": 4.2553191489361704e-07, "loss": 4.593955993652344, "step": 5 }, { "epoch": 0.01929260450160772, "grad_norm": 35.40565048454064, "learning_rate": 5.319148936170213e-07, "loss": 4.042428016662598, "step": 6 }, { "epoch": 0.022508038585209004, "grad_norm": 33.35178240422259, "learning_rate": 6.382978723404255e-07, "loss": 4.12535285949707, "step": 7 }, { "epoch": 0.02572347266881029, "grad_norm": 30.900117272078198, "learning_rate": 7.446808510638298e-07, "loss": 3.521498680114746, "step": 8 }, { "epoch": 0.028938906752411574, "grad_norm": 30.636501853074883, "learning_rate": 8.510638297872341e-07, "loss": 3.6315274238586426, "step": 9 }, { "epoch": 0.03215434083601286, "grad_norm": 38.64870494238772, "learning_rate": 9.574468085106384e-07, "loss": 4.302469730377197, "step": 10 }, { "epoch": 0.03536977491961415, "grad_norm": 32.91754594782006, "learning_rate": 1.0638297872340427e-06, "loss": 4.56865119934082, "step": 11 }, { "epoch": 0.03858520900321544, "grad_norm": 34.58013362254361, "learning_rate": 1.170212765957447e-06, "loss": 4.283186912536621, "step": 12 }, { "epoch": 0.04180064308681672, "grad_norm": 40.581705970195586, "learning_rate": 1.276595744680851e-06, "loss": 4.2185187339782715, "step": 13 }, { "epoch": 0.04501607717041801, "grad_norm": 29.29283904903904, "learning_rate": 1.3829787234042555e-06, "loss": 3.8783042430877686, "step": 14 }, { "epoch": 0.04823151125401929, "grad_norm": 27.27991833133174, "learning_rate": 1.4893617021276596e-06, "loss": 4.050146579742432, "step": 15 }, { "epoch": 0.05144694533762058, "grad_norm": 27.999481136276096, "learning_rate": 1.595744680851064e-06, "loss": 3.825010299682617, "step": 16 }, { "epoch": 0.05466237942122187, "grad_norm": 22.536982883463256, "learning_rate": 1.7021276595744682e-06, "loss": 3.562378406524658, "step": 17 }, { "epoch": 0.05787781350482315, "grad_norm": 34.480722847374665, "learning_rate": 1.8085106382978727e-06, "loss": 3.8451032638549805, "step": 18 }, { "epoch": 0.06109324758842444, "grad_norm": 18.624534731891554, "learning_rate": 1.9148936170212767e-06, "loss": 3.538512945175171, "step": 19 }, { "epoch": 0.06430868167202572, "grad_norm": 12.727844125034615, "learning_rate": 2.021276595744681e-06, "loss": 3.4035849571228027, "step": 20 }, { "epoch": 0.06752411575562701, "grad_norm": 16.628683791330275, "learning_rate": 2.1276595744680853e-06, "loss": 4.060901165008545, "step": 21 }, { "epoch": 0.0707395498392283, "grad_norm": 15.851111458013285, "learning_rate": 2.2340425531914894e-06, "loss": 3.4492287635803223, "step": 22 }, { "epoch": 0.07395498392282958, "grad_norm": 14.753226693275314, "learning_rate": 2.340425531914894e-06, "loss": 3.4821548461914062, "step": 23 }, { "epoch": 0.07717041800643087, "grad_norm": 13.046614909449563, "learning_rate": 2.446808510638298e-06, "loss": 2.6914403438568115, "step": 24 }, { "epoch": 0.08038585209003216, "grad_norm": 10.833167684511187, "learning_rate": 2.553191489361702e-06, "loss": 3.381208896636963, "step": 25 }, { "epoch": 0.08360128617363344, "grad_norm": 14.663957003362531, "learning_rate": 2.6595744680851065e-06, "loss": 3.723344564437866, "step": 26 }, { "epoch": 0.08681672025723473, "grad_norm": 12.38492722838179, "learning_rate": 2.765957446808511e-06, "loss": 3.4975712299346924, "step": 27 }, { "epoch": 0.09003215434083602, "grad_norm": 11.401609720183584, "learning_rate": 2.8723404255319155e-06, "loss": 3.742828369140625, "step": 28 }, { "epoch": 0.0932475884244373, "grad_norm": 12.794559143366632, "learning_rate": 2.978723404255319e-06, "loss": 3.7880096435546875, "step": 29 }, { "epoch": 0.09646302250803858, "grad_norm": 26.7679703474409, "learning_rate": 3.0851063829787237e-06, "loss": 3.091320037841797, "step": 30 }, { "epoch": 0.09967845659163987, "grad_norm": 11.726188149872904, "learning_rate": 3.191489361702128e-06, "loss": 3.397942543029785, "step": 31 }, { "epoch": 0.10289389067524116, "grad_norm": 11.535658534446908, "learning_rate": 3.297872340425532e-06, "loss": 3.3407297134399414, "step": 32 }, { "epoch": 0.10610932475884244, "grad_norm": 12.230466594907684, "learning_rate": 3.4042553191489363e-06, "loss": 3.5374701023101807, "step": 33 }, { "epoch": 0.10932475884244373, "grad_norm": 17.243624644167863, "learning_rate": 3.510638297872341e-06, "loss": 3.028085708618164, "step": 34 }, { "epoch": 0.11254019292604502, "grad_norm": 17.334038622045792, "learning_rate": 3.6170212765957453e-06, "loss": 3.191539764404297, "step": 35 }, { "epoch": 0.1157556270096463, "grad_norm": 14.86079639907893, "learning_rate": 3.723404255319149e-06, "loss": 3.315582275390625, "step": 36 }, { "epoch": 0.1189710610932476, "grad_norm": 13.609433504610683, "learning_rate": 3.8297872340425535e-06, "loss": 3.1429853439331055, "step": 37 }, { "epoch": 0.12218649517684887, "grad_norm": 12.204605042968506, "learning_rate": 3.936170212765958e-06, "loss": 3.2580060958862305, "step": 38 }, { "epoch": 0.12540192926045016, "grad_norm": 9.319212608299305, "learning_rate": 4.042553191489362e-06, "loss": 2.8858089447021484, "step": 39 }, { "epoch": 0.12861736334405144, "grad_norm": 12.524532210698558, "learning_rate": 4.148936170212766e-06, "loss": 3.385632038116455, "step": 40 }, { "epoch": 0.13183279742765272, "grad_norm": 8.648905095426267, "learning_rate": 4.255319148936171e-06, "loss": 2.8703691959381104, "step": 41 }, { "epoch": 0.13504823151125403, "grad_norm": 13.669866742395188, "learning_rate": 4.361702127659575e-06, "loss": 3.3186304569244385, "step": 42 }, { "epoch": 0.1382636655948553, "grad_norm": 13.513984643274535, "learning_rate": 4.468085106382979e-06, "loss": 3.2565927505493164, "step": 43 }, { "epoch": 0.1414790996784566, "grad_norm": 11.467838472357526, "learning_rate": 4.574468085106383e-06, "loss": 3.012521982192993, "step": 44 }, { "epoch": 0.14469453376205788, "grad_norm": 14.414224190053467, "learning_rate": 4.680851063829788e-06, "loss": 3.093921184539795, "step": 45 }, { "epoch": 0.14790996784565916, "grad_norm": 13.083779631573304, "learning_rate": 4.787234042553192e-06, "loss": 3.1773462295532227, "step": 46 }, { "epoch": 0.15112540192926044, "grad_norm": 10.99722367362911, "learning_rate": 4.893617021276596e-06, "loss": 2.971510648727417, "step": 47 }, { "epoch": 0.15434083601286175, "grad_norm": 11.68667724946745, "learning_rate": 5e-06, "loss": 3.365861415863037, "step": 48 }, { "epoch": 0.15755627009646303, "grad_norm": 12.098124814579858, "learning_rate": 5.106382978723404e-06, "loss": 3.331052780151367, "step": 49 }, { "epoch": 0.1607717041800643, "grad_norm": 15.052059643954104, "learning_rate": 5.212765957446809e-06, "loss": 3.513488292694092, "step": 50 }, { "epoch": 0.1639871382636656, "grad_norm": 11.566325521455326, "learning_rate": 5.319148936170213e-06, "loss": 3.165461540222168, "step": 51 }, { "epoch": 0.16720257234726688, "grad_norm": 9.34326584922921, "learning_rate": 5.425531914893617e-06, "loss": 3.308755397796631, "step": 52 }, { "epoch": 0.17041800643086816, "grad_norm": 8.081169045448624, "learning_rate": 5.531914893617022e-06, "loss": 2.905186653137207, "step": 53 }, { "epoch": 0.17363344051446947, "grad_norm": 7.992815413183043, "learning_rate": 5.638297872340426e-06, "loss": 3.2160592079162598, "step": 54 }, { "epoch": 0.17684887459807075, "grad_norm": 13.368580785667488, "learning_rate": 5.744680851063831e-06, "loss": 2.809837818145752, "step": 55 }, { "epoch": 0.18006430868167203, "grad_norm": 12.22993319530342, "learning_rate": 5.851063829787235e-06, "loss": 3.355532646179199, "step": 56 }, { "epoch": 0.1832797427652733, "grad_norm": 7.221255459808142, "learning_rate": 5.957446808510638e-06, "loss": 2.912825584411621, "step": 57 }, { "epoch": 0.1864951768488746, "grad_norm": 8.99412347483827, "learning_rate": 6.063829787234044e-06, "loss": 2.738528251647949, "step": 58 }, { "epoch": 0.18971061093247588, "grad_norm": 9.344015814293519, "learning_rate": 6.170212765957447e-06, "loss": 3.5236358642578125, "step": 59 }, { "epoch": 0.19292604501607716, "grad_norm": 9.156439246600511, "learning_rate": 6.276595744680851e-06, "loss": 2.438237190246582, "step": 60 }, { "epoch": 0.19614147909967847, "grad_norm": 13.840159967058424, "learning_rate": 6.382978723404256e-06, "loss": 3.002664804458618, "step": 61 }, { "epoch": 0.19935691318327975, "grad_norm": 19.877275319550726, "learning_rate": 6.48936170212766e-06, "loss": 2.6102824211120605, "step": 62 }, { "epoch": 0.20257234726688103, "grad_norm": 12.1602713562138, "learning_rate": 6.595744680851064e-06, "loss": 2.8119864463806152, "step": 63 }, { "epoch": 0.2057877813504823, "grad_norm": 16.720203965795687, "learning_rate": 6.702127659574469e-06, "loss": 3.0033774375915527, "step": 64 }, { "epoch": 0.2090032154340836, "grad_norm": 11.940414659790333, "learning_rate": 6.808510638297873e-06, "loss": 3.0424952507019043, "step": 65 }, { "epoch": 0.21221864951768488, "grad_norm": 13.529947357143289, "learning_rate": 6.914893617021278e-06, "loss": 3.125572443008423, "step": 66 }, { "epoch": 0.21543408360128619, "grad_norm": 14.39004817757797, "learning_rate": 7.021276595744682e-06, "loss": 2.6417791843414307, "step": 67 }, { "epoch": 0.21864951768488747, "grad_norm": 10.746950415723779, "learning_rate": 7.127659574468085e-06, "loss": 2.795292615890503, "step": 68 }, { "epoch": 0.22186495176848875, "grad_norm": 8.800102366100415, "learning_rate": 7.234042553191491e-06, "loss": 2.806095600128174, "step": 69 }, { "epoch": 0.22508038585209003, "grad_norm": 9.675471278291617, "learning_rate": 7.340425531914894e-06, "loss": 3.1251420974731445, "step": 70 }, { "epoch": 0.2282958199356913, "grad_norm": 10.053887771078337, "learning_rate": 7.446808510638298e-06, "loss": 3.1366963386535645, "step": 71 }, { "epoch": 0.2315112540192926, "grad_norm": 9.96554198597255, "learning_rate": 7.553191489361703e-06, "loss": 2.7942872047424316, "step": 72 }, { "epoch": 0.2347266881028939, "grad_norm": 9.128869915479399, "learning_rate": 7.659574468085107e-06, "loss": 2.7176175117492676, "step": 73 }, { "epoch": 0.2379421221864952, "grad_norm": 28.173273740714603, "learning_rate": 7.765957446808511e-06, "loss": 3.2510626316070557, "step": 74 }, { "epoch": 0.24115755627009647, "grad_norm": 15.875524782572642, "learning_rate": 7.872340425531916e-06, "loss": 3.5180716514587402, "step": 75 }, { "epoch": 0.24437299035369775, "grad_norm": 8.411231774581736, "learning_rate": 7.97872340425532e-06, "loss": 2.6583242416381836, "step": 76 }, { "epoch": 0.24758842443729903, "grad_norm": 10.255213693759098, "learning_rate": 8.085106382978723e-06, "loss": 3.522376537322998, "step": 77 }, { "epoch": 0.2508038585209003, "grad_norm": 14.129242001151896, "learning_rate": 8.191489361702128e-06, "loss": 2.666438102722168, "step": 78 }, { "epoch": 0.2540192926045016, "grad_norm": 13.280551504579265, "learning_rate": 8.297872340425532e-06, "loss": 3.0438873767852783, "step": 79 }, { "epoch": 0.2572347266881029, "grad_norm": 9.282380199453716, "learning_rate": 8.404255319148937e-06, "loss": 2.7416107654571533, "step": 80 }, { "epoch": 0.2604501607717042, "grad_norm": 13.819155087109117, "learning_rate": 8.510638297872341e-06, "loss": 3.040888547897339, "step": 81 }, { "epoch": 0.26366559485530544, "grad_norm": 10.236048490196817, "learning_rate": 8.617021276595746e-06, "loss": 2.8178224563598633, "step": 82 }, { "epoch": 0.26688102893890675, "grad_norm": 11.247565366748827, "learning_rate": 8.72340425531915e-06, "loss": 3.13818097114563, "step": 83 }, { "epoch": 0.27009646302250806, "grad_norm": 11.38311149290456, "learning_rate": 8.829787234042555e-06, "loss": 3.0007710456848145, "step": 84 }, { "epoch": 0.2733118971061093, "grad_norm": 15.216874845868524, "learning_rate": 8.936170212765958e-06, "loss": 2.1240034103393555, "step": 85 }, { "epoch": 0.2765273311897106, "grad_norm": 14.569359980649596, "learning_rate": 9.042553191489362e-06, "loss": 3.0258898735046387, "step": 86 }, { "epoch": 0.2797427652733119, "grad_norm": 10.551293545168425, "learning_rate": 9.148936170212767e-06, "loss": 3.815779685974121, "step": 87 }, { "epoch": 0.2829581993569132, "grad_norm": 13.73383748688779, "learning_rate": 9.255319148936171e-06, "loss": 3.146327018737793, "step": 88 }, { "epoch": 0.2861736334405145, "grad_norm": 16.606288521806196, "learning_rate": 9.361702127659576e-06, "loss": 3.730978488922119, "step": 89 }, { "epoch": 0.28938906752411575, "grad_norm": 15.589892740807427, "learning_rate": 9.46808510638298e-06, "loss": 2.837461471557617, "step": 90 }, { "epoch": 0.29260450160771706, "grad_norm": 8.969993651783593, "learning_rate": 9.574468085106385e-06, "loss": 2.8579788208007812, "step": 91 }, { "epoch": 0.2958199356913183, "grad_norm": 7.662931624851478, "learning_rate": 9.680851063829787e-06, "loss": 3.059731960296631, "step": 92 }, { "epoch": 0.2990353697749196, "grad_norm": 12.506461029325436, "learning_rate": 9.787234042553192e-06, "loss": 2.419557809829712, "step": 93 }, { "epoch": 0.3022508038585209, "grad_norm": 11.680821462164978, "learning_rate": 9.893617021276596e-06, "loss": 2.8333683013916016, "step": 94 }, { "epoch": 0.3054662379421222, "grad_norm": 12.174316986589778, "learning_rate": 1e-05, "loss": 2.74963641166687, "step": 95 }, { "epoch": 0.3086816720257235, "grad_norm": 11.199762414211195, "learning_rate": 9.999964947796453e-06, "loss": 2.873091697692871, "step": 96 }, { "epoch": 0.31189710610932475, "grad_norm": 13.974152571943035, "learning_rate": 9.999859791677274e-06, "loss": 2.7511343955993652, "step": 97 }, { "epoch": 0.31511254019292606, "grad_norm": 7.263607356101665, "learning_rate": 9.999684533116843e-06, "loss": 2.71083927154541, "step": 98 }, { "epoch": 0.3183279742765273, "grad_norm": 25.796622294537844, "learning_rate": 9.999439174572441e-06, "loss": 3.5184683799743652, "step": 99 }, { "epoch": 0.3215434083601286, "grad_norm": 17.664679448204584, "learning_rate": 9.999123719484209e-06, "loss": 3.0679643154144287, "step": 100 }, { "epoch": 0.3247588424437299, "grad_norm": 8.788378126441323, "learning_rate": 9.99873817227511e-06, "loss": 3.4208366870880127, "step": 101 }, { "epoch": 0.3279742765273312, "grad_norm": 10.180060028116147, "learning_rate": 9.998282538350849e-06, "loss": 2.5970406532287598, "step": 102 }, { "epoch": 0.3311897106109325, "grad_norm": 8.806422861108551, "learning_rate": 9.997756824099822e-06, "loss": 2.414546012878418, "step": 103 }, { "epoch": 0.33440514469453375, "grad_norm": 7.16593228968872, "learning_rate": 9.997161036893001e-06, "loss": 2.7526440620422363, "step": 104 }, { "epoch": 0.33762057877813506, "grad_norm": 17.516673563240467, "learning_rate": 9.996495185083853e-06, "loss": 3.5313873291015625, "step": 105 }, { "epoch": 0.3408360128617363, "grad_norm": 11.176485057675038, "learning_rate": 9.995759278008202e-06, "loss": 3.215785026550293, "step": 106 }, { "epoch": 0.3440514469453376, "grad_norm": 10.013772937565832, "learning_rate": 9.994953325984116e-06, "loss": 2.8342652320861816, "step": 107 }, { "epoch": 0.34726688102893893, "grad_norm": 16.13725758624622, "learning_rate": 9.994077340311751e-06, "loss": 3.187843084335327, "step": 108 }, { "epoch": 0.3504823151125402, "grad_norm": 13.142839661126178, "learning_rate": 9.993131333273203e-06, "loss": 3.329102039337158, "step": 109 }, { "epoch": 0.3536977491961415, "grad_norm": 13.15304975587744, "learning_rate": 9.99211531813232e-06, "loss": 2.963022232055664, "step": 110 }, { "epoch": 0.35691318327974275, "grad_norm": 20.764351097324777, "learning_rate": 9.991029309134533e-06, "loss": 3.1603951454162598, "step": 111 }, { "epoch": 0.36012861736334406, "grad_norm": 20.990534185345496, "learning_rate": 9.989873321506643e-06, "loss": 3.063810110092163, "step": 112 }, { "epoch": 0.3633440514469453, "grad_norm": 11.652596742212573, "learning_rate": 9.988647371456614e-06, "loss": 3.0116543769836426, "step": 113 }, { "epoch": 0.3665594855305466, "grad_norm": 19.438695012900585, "learning_rate": 9.987351476173352e-06, "loss": 3.010406255722046, "step": 114 }, { "epoch": 0.36977491961414793, "grad_norm": 6.079653142271714, "learning_rate": 9.985985653826444e-06, "loss": 1.9504810571670532, "step": 115 }, { "epoch": 0.3729903536977492, "grad_norm": 13.795243277642982, "learning_rate": 9.98454992356593e-06, "loss": 2.93680739402771, "step": 116 }, { "epoch": 0.3762057877813505, "grad_norm": 13.003967588877996, "learning_rate": 9.983044305522007e-06, "loss": 2.3677353858947754, "step": 117 }, { "epoch": 0.37942122186495175, "grad_norm": 18.380499765458158, "learning_rate": 9.981468820804774e-06, "loss": 2.847960948944092, "step": 118 }, { "epoch": 0.38263665594855306, "grad_norm": 9.899382867106105, "learning_rate": 9.979823491503909e-06, "loss": 3.0923283100128174, "step": 119 }, { "epoch": 0.3858520900321543, "grad_norm": 28.34535742986171, "learning_rate": 9.978108340688383e-06, "loss": 3.020812511444092, "step": 120 }, { "epoch": 0.3890675241157556, "grad_norm": 9.019875841237615, "learning_rate": 9.976323392406122e-06, "loss": 3.3838634490966797, "step": 121 }, { "epoch": 0.39228295819935693, "grad_norm": 23.495664363464023, "learning_rate": 9.974468671683673e-06, "loss": 3.5906333923339844, "step": 122 }, { "epoch": 0.3954983922829582, "grad_norm": 10.641890312294386, "learning_rate": 9.972544204525853e-06, "loss": 3.000471591949463, "step": 123 }, { "epoch": 0.3987138263665595, "grad_norm": 9.496581002852425, "learning_rate": 9.970550017915393e-06, "loss": 2.9725592136383057, "step": 124 }, { "epoch": 0.40192926045016075, "grad_norm": 20.913334058741135, "learning_rate": 9.968486139812544e-06, "loss": 3.160482406616211, "step": 125 }, { "epoch": 0.40514469453376206, "grad_norm": 11.751298309185795, "learning_rate": 9.966352599154697e-06, "loss": 3.0642364025115967, "step": 126 }, { "epoch": 0.40836012861736337, "grad_norm": 20.856740980507603, "learning_rate": 9.964149425855971e-06, "loss": 3.73250675201416, "step": 127 }, { "epoch": 0.4115755627009646, "grad_norm": 9.151325730059728, "learning_rate": 9.961876650806799e-06, "loss": 2.632124900817871, "step": 128 }, { "epoch": 0.41479099678456594, "grad_norm": 11.4247472974135, "learning_rate": 9.95953430587349e-06, "loss": 2.5810580253601074, "step": 129 }, { "epoch": 0.4180064308681672, "grad_norm": 16.431822779962932, "learning_rate": 9.957122423897786e-06, "loss": 3.170461654663086, "step": 130 }, { "epoch": 0.4212218649517685, "grad_norm": 21.943673264965508, "learning_rate": 9.954641038696395e-06, "loss": 3.044951915740967, "step": 131 }, { "epoch": 0.42443729903536975, "grad_norm": 6.71332684009912, "learning_rate": 9.952090185060528e-06, "loss": 2.9257850646972656, "step": 132 }, { "epoch": 0.42765273311897106, "grad_norm": 9.885222299724687, "learning_rate": 9.9494698987554e-06, "loss": 2.943833827972412, "step": 133 }, { "epoch": 0.43086816720257237, "grad_norm": 11.16095425096583, "learning_rate": 9.946780216519734e-06, "loss": 3.022878646850586, "step": 134 }, { "epoch": 0.4340836012861736, "grad_norm": 9.033329511785515, "learning_rate": 9.944021176065247e-06, "loss": 2.792724847793579, "step": 135 }, { "epoch": 0.43729903536977494, "grad_norm": 13.435034889452208, "learning_rate": 9.941192816076114e-06, "loss": 3.35680890083313, "step": 136 }, { "epoch": 0.4405144694533762, "grad_norm": 6.768294617543249, "learning_rate": 9.938295176208441e-06, "loss": 2.4593820571899414, "step": 137 }, { "epoch": 0.4437299035369775, "grad_norm": 14.633684351350666, "learning_rate": 9.93532829708969e-06, "loss": 2.6255781650543213, "step": 138 }, { "epoch": 0.44694533762057875, "grad_norm": 16.68694895086861, "learning_rate": 9.932292220318121e-06, "loss": 2.6132946014404297, "step": 139 }, { "epoch": 0.45016077170418006, "grad_norm": 15.726897720613817, "learning_rate": 9.929186988462208e-06, "loss": 2.9322824478149414, "step": 140 }, { "epoch": 0.4533762057877814, "grad_norm": 15.761243450650786, "learning_rate": 9.926012645060037e-06, "loss": 2.601005792617798, "step": 141 }, { "epoch": 0.4565916398713826, "grad_norm": 36.62478666800511, "learning_rate": 9.9227692346187e-06, "loss": 2.5554819107055664, "step": 142 }, { "epoch": 0.45980707395498394, "grad_norm": 12.187964367204458, "learning_rate": 9.919456802613672e-06, "loss": 2.5176918506622314, "step": 143 }, { "epoch": 0.4630225080385852, "grad_norm": 17.390325809468337, "learning_rate": 9.916075395488167e-06, "loss": 2.341370105743408, "step": 144 }, { "epoch": 0.4662379421221865, "grad_norm": 12.718168513574046, "learning_rate": 9.912625060652496e-06, "loss": 3.2781105041503906, "step": 145 }, { "epoch": 0.4694533762057878, "grad_norm": 13.449199904281418, "learning_rate": 9.909105846483394e-06, "loss": 3.615126132965088, "step": 146 }, { "epoch": 0.47266881028938906, "grad_norm": 8.050446777669299, "learning_rate": 9.905517802323345e-06, "loss": 2.8603837490081787, "step": 147 }, { "epoch": 0.4758842443729904, "grad_norm": 12.943386027137832, "learning_rate": 9.901860978479889e-06, "loss": 2.465343952178955, "step": 148 }, { "epoch": 0.4790996784565916, "grad_norm": 49.15991413291505, "learning_rate": 9.898135426224923e-06, "loss": 3.241806983947754, "step": 149 }, { "epoch": 0.48231511254019294, "grad_norm": 17.678071991265508, "learning_rate": 9.89434119779397e-06, "loss": 3.292675018310547, "step": 150 }, { "epoch": 0.4855305466237942, "grad_norm": 15.424220522820049, "learning_rate": 9.89047834638546e-06, "loss": 2.6159539222717285, "step": 151 }, { "epoch": 0.4887459807073955, "grad_norm": 6.510280246958492, "learning_rate": 9.886546926159972e-06, "loss": 2.4839179515838623, "step": 152 }, { "epoch": 0.4919614147909968, "grad_norm": 11.741972927177837, "learning_rate": 9.882546992239483e-06, "loss": 2.995469570159912, "step": 153 }, { "epoch": 0.49517684887459806, "grad_norm": 13.630320770906891, "learning_rate": 9.878478600706595e-06, "loss": 3.255875587463379, "step": 154 }, { "epoch": 0.4983922829581994, "grad_norm": 36.221839717193376, "learning_rate": 9.87434180860374e-06, "loss": 3.4806838035583496, "step": 155 }, { "epoch": 0.5016077170418006, "grad_norm": 15.136927688596392, "learning_rate": 9.87013667393239e-06, "loss": 3.202141284942627, "step": 156 }, { "epoch": 0.5048231511254019, "grad_norm": 21.095472411241253, "learning_rate": 9.865863255652242e-06, "loss": 2.8557021617889404, "step": 157 }, { "epoch": 0.5080385852090032, "grad_norm": 9.121385453492111, "learning_rate": 9.861521613680384e-06, "loss": 2.9327592849731445, "step": 158 }, { "epoch": 0.5112540192926045, "grad_norm": 8.35474008993999, "learning_rate": 9.857111808890465e-06, "loss": 3.2285704612731934, "step": 159 }, { "epoch": 0.5144694533762058, "grad_norm": 14.002125724500594, "learning_rate": 9.852633903111834e-06, "loss": 2.7799017429351807, "step": 160 }, { "epoch": 0.5176848874598071, "grad_norm": 12.65627846068601, "learning_rate": 9.848087959128679e-06, "loss": 2.5985677242279053, "step": 161 }, { "epoch": 0.5209003215434084, "grad_norm": 14.086117584953953, "learning_rate": 9.843474040679137e-06, "loss": 3.1218137741088867, "step": 162 }, { "epoch": 0.5241157556270096, "grad_norm": 8.527738044773436, "learning_rate": 9.838792212454416e-06, "loss": 2.367370367050171, "step": 163 }, { "epoch": 0.5273311897106109, "grad_norm": 9.981924505220025, "learning_rate": 9.834042540097875e-06, "loss": 2.8083603382110596, "step": 164 }, { "epoch": 0.5305466237942122, "grad_norm": 11.46020527117729, "learning_rate": 9.829225090204102e-06, "loss": 2.920241117477417, "step": 165 }, { "epoch": 0.5337620578778135, "grad_norm": 12.469087819796588, "learning_rate": 9.824339930317994e-06, "loss": 2.6172094345092773, "step": 166 }, { "epoch": 0.5369774919614148, "grad_norm": 20.922191531715136, "learning_rate": 9.819387128933799e-06, "loss": 3.1109981536865234, "step": 167 }, { "epoch": 0.5401929260450161, "grad_norm": 15.632738580412314, "learning_rate": 9.814366755494155e-06, "loss": 3.153048038482666, "step": 168 }, { "epoch": 0.5434083601286174, "grad_norm": 35.82397708735359, "learning_rate": 9.809278880389126e-06, "loss": 3.2571372985839844, "step": 169 }, { "epoch": 0.5466237942122186, "grad_norm": 8.554787244670667, "learning_rate": 9.804123574955202e-06, "loss": 3.108255624771118, "step": 170 }, { "epoch": 0.5498392282958199, "grad_norm": 7.383101110488588, "learning_rate": 9.798900911474315e-06, "loss": 3.0177969932556152, "step": 171 }, { "epoch": 0.5530546623794212, "grad_norm": 11.293545889392764, "learning_rate": 9.793610963172802e-06, "loss": 2.795715093612671, "step": 172 }, { "epoch": 0.5562700964630225, "grad_norm": 21.241938441534675, "learning_rate": 9.78825380422041e-06, "loss": 3.3412439823150635, "step": 173 }, { "epoch": 0.5594855305466238, "grad_norm": 9.87643076192503, "learning_rate": 9.78282950972922e-06, "loss": 2.7117419242858887, "step": 174 }, { "epoch": 0.5627009646302251, "grad_norm": 10.242385683099888, "learning_rate": 9.77733815575263e-06, "loss": 3.1940979957580566, "step": 175 }, { "epoch": 0.5659163987138264, "grad_norm": 13.773999328309266, "learning_rate": 9.771779819284257e-06, "loss": 2.418674945831299, "step": 176 }, { "epoch": 0.5691318327974276, "grad_norm": 18.81855085740899, "learning_rate": 9.766154578256883e-06, "loss": 2.819211959838867, "step": 177 }, { "epoch": 0.572347266881029, "grad_norm": 18.832073296958836, "learning_rate": 9.76046251154134e-06, "loss": 3.260634183883667, "step": 178 }, { "epoch": 0.5755627009646302, "grad_norm": 14.459091987874368, "learning_rate": 9.754703698945425e-06, "loss": 3.002488136291504, "step": 179 }, { "epoch": 0.5787781350482315, "grad_norm": 9.482812229157702, "learning_rate": 9.748878221212763e-06, "loss": 3.066258668899536, "step": 180 }, { "epoch": 0.5819935691318328, "grad_norm": 12.867585721735884, "learning_rate": 9.742986160021688e-06, "loss": 3.4351935386657715, "step": 181 }, { "epoch": 0.5852090032154341, "grad_norm": 10.802517130903386, "learning_rate": 9.73702759798409e-06, "loss": 3.2599828243255615, "step": 182 }, { "epoch": 0.5884244372990354, "grad_norm": 24.934825581625855, "learning_rate": 9.731002618644265e-06, "loss": 2.5718865394592285, "step": 183 }, { "epoch": 0.5916398713826366, "grad_norm": 20.787769842276045, "learning_rate": 9.724911306477729e-06, "loss": 2.765693426132202, "step": 184 }, { "epoch": 0.594855305466238, "grad_norm": 9.109874314786204, "learning_rate": 9.71875374689005e-06, "loss": 3.426023244857788, "step": 185 }, { "epoch": 0.5980707395498392, "grad_norm": 21.279795009176986, "learning_rate": 9.71253002621564e-06, "loss": 3.001716375350952, "step": 186 }, { "epoch": 0.6012861736334405, "grad_norm": 10.787659736048406, "learning_rate": 9.706240231716549e-06, "loss": 2.950758218765259, "step": 187 }, { "epoch": 0.6045016077170418, "grad_norm": 12.733718582846585, "learning_rate": 9.699884451581238e-06, "loss": 3.2297606468200684, "step": 188 }, { "epoch": 0.6077170418006431, "grad_norm": 12.774631438040222, "learning_rate": 9.693462774923351e-06, "loss": 4.231553077697754, "step": 189 }, { "epoch": 0.6109324758842444, "grad_norm": 7.991710258799094, "learning_rate": 9.686975291780449e-06, "loss": 3.427185535430908, "step": 190 }, { "epoch": 0.6141479099678456, "grad_norm": 8.091734891391763, "learning_rate": 9.68042209311277e-06, "loss": 3.104320526123047, "step": 191 }, { "epoch": 0.617363344051447, "grad_norm": 9.939232309092867, "learning_rate": 9.67380327080193e-06, "loss": 2.5996108055114746, "step": 192 }, { "epoch": 0.6205787781350482, "grad_norm": 15.107188854133135, "learning_rate": 9.667118917649656e-06, "loss": 2.6025047302246094, "step": 193 }, { "epoch": 0.6237942122186495, "grad_norm": 13.565146098612988, "learning_rate": 9.660369127376469e-06, "loss": 2.7667369842529297, "step": 194 }, { "epoch": 0.6270096463022508, "grad_norm": 12.27977824054795, "learning_rate": 9.653553994620378e-06, "loss": 2.9813175201416016, "step": 195 }, { "epoch": 0.6302250803858521, "grad_norm": 16.18068581074389, "learning_rate": 9.64667361493555e-06, "loss": 3.094072103500366, "step": 196 }, { "epoch": 0.6334405144694534, "grad_norm": 7.584418927697848, "learning_rate": 9.639728084790976e-06, "loss": 2.9591763019561768, "step": 197 }, { "epoch": 0.6366559485530546, "grad_norm": 6.415026684299775, "learning_rate": 9.632717501569106e-06, "loss": 1.9626116752624512, "step": 198 }, { "epoch": 0.639871382636656, "grad_norm": 21.919505536575453, "learning_rate": 9.6256419635645e-06, "loss": 3.0262200832366943, "step": 199 }, { "epoch": 0.6430868167202572, "grad_norm": 9.532554532436253, "learning_rate": 9.618501569982437e-06, "loss": 2.373394012451172, "step": 200 }, { "epoch": 0.6463022508038585, "grad_norm": 9.33134950216214, "learning_rate": 9.611296420937526e-06, "loss": 2.601590633392334, "step": 201 }, { "epoch": 0.6495176848874598, "grad_norm": 13.972297231734744, "learning_rate": 9.60402661745231e-06, "loss": 3.3032302856445312, "step": 202 }, { "epoch": 0.6527331189710611, "grad_norm": 12.123983986715679, "learning_rate": 9.59669226145584e-06, "loss": 2.55745267868042, "step": 203 }, { "epoch": 0.6559485530546624, "grad_norm": 13.044678435205267, "learning_rate": 9.589293455782253e-06, "loss": 3.162076950073242, "step": 204 }, { "epoch": 0.6591639871382636, "grad_norm": 12.717015520085477, "learning_rate": 9.581830304169325e-06, "loss": 3.104783535003662, "step": 205 }, { "epoch": 0.662379421221865, "grad_norm": 10.909068293638112, "learning_rate": 9.574302911257021e-06, "loss": 1.5882987976074219, "step": 206 }, { "epoch": 0.6655948553054662, "grad_norm": 16.856966099264525, "learning_rate": 9.566711382586022e-06, "loss": 3.12563157081604, "step": 207 }, { "epoch": 0.6688102893890675, "grad_norm": 8.178490711172556, "learning_rate": 9.559055824596252e-06, "loss": 2.5417189598083496, "step": 208 }, { "epoch": 0.6720257234726688, "grad_norm": 24.246438880890675, "learning_rate": 9.551336344625387e-06, "loss": 3.221043109893799, "step": 209 }, { "epoch": 0.6752411575562701, "grad_norm": 8.34315714768651, "learning_rate": 9.543553050907332e-06, "loss": 2.767820358276367, "step": 210 }, { "epoch": 0.6784565916398714, "grad_norm": 28.687273320967922, "learning_rate": 9.53570605257073e-06, "loss": 4.299283027648926, "step": 211 }, { "epoch": 0.6816720257234726, "grad_norm": 9.232214067792807, "learning_rate": 9.527795459637413e-06, "loss": 2.867112398147583, "step": 212 }, { "epoch": 0.684887459807074, "grad_norm": 14.46539808412858, "learning_rate": 9.519821383020866e-06, "loss": 2.6538944244384766, "step": 213 }, { "epoch": 0.6881028938906752, "grad_norm": 16.762492706972427, "learning_rate": 9.511783934524674e-06, "loss": 3.379420280456543, "step": 214 }, { "epoch": 0.6913183279742765, "grad_norm": 11.417167539665027, "learning_rate": 9.503683226840948e-06, "loss": 2.9065451622009277, "step": 215 }, { "epoch": 0.6945337620578779, "grad_norm": 8.688764296327069, "learning_rate": 9.495519373548748e-06, "loss": 2.9622750282287598, "step": 216 }, { "epoch": 0.6977491961414791, "grad_norm": 17.306753656078968, "learning_rate": 9.487292489112497e-06, "loss": 3.1384975910186768, "step": 217 }, { "epoch": 0.7009646302250804, "grad_norm": 9.278446527178623, "learning_rate": 9.479002688880362e-06, "loss": 3.00459623336792, "step": 218 }, { "epoch": 0.7041800643086816, "grad_norm": 8.829166062791868, "learning_rate": 9.470650089082649e-06, "loss": 3.349134922027588, "step": 219 }, { "epoch": 0.707395498392283, "grad_norm": 8.252383756187383, "learning_rate": 9.462234806830172e-06, "loss": 2.8735666275024414, "step": 220 }, { "epoch": 0.7106109324758842, "grad_norm": 10.10461049277595, "learning_rate": 9.453756960112605e-06, "loss": 2.7908334732055664, "step": 221 }, { "epoch": 0.7138263665594855, "grad_norm": 11.263066058506535, "learning_rate": 9.445216667796833e-06, "loss": 2.5783145427703857, "step": 222 }, { "epoch": 0.7170418006430869, "grad_norm": 19.60227612362862, "learning_rate": 9.436614049625277e-06, "loss": 2.7622079849243164, "step": 223 }, { "epoch": 0.7202572347266881, "grad_norm": 20.895857573617988, "learning_rate": 9.42794922621423e-06, "loss": 3.2321324348449707, "step": 224 }, { "epoch": 0.7234726688102894, "grad_norm": 23.420564933331203, "learning_rate": 9.419222319052154e-06, "loss": 2.5579419136047363, "step": 225 }, { "epoch": 0.7266881028938906, "grad_norm": 12.853985003804183, "learning_rate": 9.410433450497977e-06, "loss": 3.260056495666504, "step": 226 }, { "epoch": 0.729903536977492, "grad_norm": 11.182131927651461, "learning_rate": 9.401582743779384e-06, "loss": 2.7521541118621826, "step": 227 }, { "epoch": 0.7331189710610932, "grad_norm": 19.802196143776204, "learning_rate": 9.392670322991085e-06, "loss": 2.986008644104004, "step": 228 }, { "epoch": 0.7363344051446945, "grad_norm": 10.66119164095427, "learning_rate": 9.383696313093073e-06, "loss": 3.1167283058166504, "step": 229 }, { "epoch": 0.7395498392282959, "grad_norm": 8.87831230718112, "learning_rate": 9.374660839908881e-06, "loss": 3.0863423347473145, "step": 230 }, { "epoch": 0.7427652733118971, "grad_norm": 16.804824808938967, "learning_rate": 9.365564030123802e-06, "loss": 3.310753345489502, "step": 231 }, { "epoch": 0.7459807073954984, "grad_norm": 14.686714392325005, "learning_rate": 9.356406011283128e-06, "loss": 2.494666576385498, "step": 232 }, { "epoch": 0.7491961414790996, "grad_norm": 12.638367443704174, "learning_rate": 9.34718691179036e-06, "loss": 3.037945508956909, "step": 233 }, { "epoch": 0.752411575562701, "grad_norm": 26.920374247029958, "learning_rate": 9.337906860905394e-06, "loss": 3.584845542907715, "step": 234 }, { "epoch": 0.7556270096463023, "grad_norm": 6.708394075133507, "learning_rate": 9.328565988742723e-06, "loss": 2.984691619873047, "step": 235 }, { "epoch": 0.7588424437299035, "grad_norm": 11.729278792048037, "learning_rate": 9.31916442626961e-06, "loss": 2.795103073120117, "step": 236 }, { "epoch": 0.7620578778135049, "grad_norm": 7.697881178490154, "learning_rate": 9.30970230530425e-06, "loss": 2.5230283737182617, "step": 237 }, { "epoch": 0.7652733118971061, "grad_norm": 8.848418169366562, "learning_rate": 9.300179758513912e-06, "loss": 2.849795341491699, "step": 238 }, { "epoch": 0.7684887459807074, "grad_norm": 9.64788428575172, "learning_rate": 9.290596919413101e-06, "loss": 2.4834206104278564, "step": 239 }, { "epoch": 0.7717041800643086, "grad_norm": 11.151899506614933, "learning_rate": 9.280953922361667e-06, "loss": 2.7844467163085938, "step": 240 }, { "epoch": 0.77491961414791, "grad_norm": 13.100289974037779, "learning_rate": 9.271250902562925e-06, "loss": 3.224181890487671, "step": 241 }, { "epoch": 0.7781350482315113, "grad_norm": 11.686317061932591, "learning_rate": 9.26148799606177e-06, "loss": 2.7271580696105957, "step": 242 }, { "epoch": 0.7813504823151125, "grad_norm": 17.10133837407015, "learning_rate": 9.251665339742751e-06, "loss": 2.834172248840332, "step": 243 }, { "epoch": 0.7845659163987139, "grad_norm": 9.175423032974624, "learning_rate": 9.24178307132817e-06, "loss": 2.8642072677612305, "step": 244 }, { "epoch": 0.7877813504823151, "grad_norm": 10.563682693957642, "learning_rate": 9.231841329376142e-06, "loss": 2.961083173751831, "step": 245 }, { "epoch": 0.7909967845659164, "grad_norm": 8.694998203842605, "learning_rate": 9.22184025327865e-06, "loss": 3.1648690700531006, "step": 246 }, { "epoch": 0.7942122186495176, "grad_norm": 13.321968130939467, "learning_rate": 9.211779983259597e-06, "loss": 2.65283203125, "step": 247 }, { "epoch": 0.797427652733119, "grad_norm": 8.370015100382718, "learning_rate": 9.201660660372835e-06, "loss": 2.8571534156799316, "step": 248 }, { "epoch": 0.8006430868167203, "grad_norm": 13.1283440171712, "learning_rate": 9.191482426500192e-06, "loss": 3.076096534729004, "step": 249 }, { "epoch": 0.8038585209003215, "grad_norm": 12.58763191241908, "learning_rate": 9.181245424349477e-06, "loss": 3.0239181518554688, "step": 250 }, { "epoch": 0.8070739549839229, "grad_norm": 10.995319596435253, "learning_rate": 9.170949797452481e-06, "loss": 2.6239326000213623, "step": 251 }, { "epoch": 0.8102893890675241, "grad_norm": 9.225322055367544, "learning_rate": 9.160595690162974e-06, "loss": 2.5555763244628906, "step": 252 }, { "epoch": 0.8135048231511254, "grad_norm": 11.507809934321713, "learning_rate": 9.15018324765466e-06, "loss": 2.371147871017456, "step": 253 }, { "epoch": 0.8167202572347267, "grad_norm": 12.469884255360506, "learning_rate": 9.139712615919163e-06, "loss": 2.494548797607422, "step": 254 }, { "epoch": 0.819935691318328, "grad_norm": 10.895498922897257, "learning_rate": 9.129183941763971e-06, "loss": 2.974158525466919, "step": 255 }, { "epoch": 0.8231511254019293, "grad_norm": 9.163142573864613, "learning_rate": 9.118597372810374e-06, "loss": 2.792419672012329, "step": 256 }, { "epoch": 0.8263665594855305, "grad_norm": 7.256984326103208, "learning_rate": 9.107953057491399e-06, "loss": 2.502934694290161, "step": 257 }, { "epoch": 0.8295819935691319, "grad_norm": 9.28895883091526, "learning_rate": 9.09725114504973e-06, "loss": 3.282193899154663, "step": 258 }, { "epoch": 0.8327974276527331, "grad_norm": 12.653451743754152, "learning_rate": 9.086491785535613e-06, "loss": 2.6221415996551514, "step": 259 }, { "epoch": 0.8360128617363344, "grad_norm": 12.157053154731505, "learning_rate": 9.07567512980475e-06, "loss": 2.594520330429077, "step": 260 }, { "epoch": 0.8392282958199357, "grad_norm": 16.45711676935307, "learning_rate": 9.064801329516192e-06, "loss": 3.279817819595337, "step": 261 }, { "epoch": 0.842443729903537, "grad_norm": 13.973378629771124, "learning_rate": 9.053870537130198e-06, "loss": 3.408698558807373, "step": 262 }, { "epoch": 0.8456591639871383, "grad_norm": 16.62805609651466, "learning_rate": 9.042882905906118e-06, "loss": 2.918642997741699, "step": 263 }, { "epoch": 0.8488745980707395, "grad_norm": 9.44966384136106, "learning_rate": 9.03183858990022e-06, "loss": 2.65049409866333, "step": 264 }, { "epoch": 0.8520900321543409, "grad_norm": 13.363066970747031, "learning_rate": 9.020737743963555e-06, "loss": 3.2480692863464355, "step": 265 }, { "epoch": 0.8553054662379421, "grad_norm": 12.666421815128665, "learning_rate": 9.009580523739763e-06, "loss": 3.1771302223205566, "step": 266 }, { "epoch": 0.8585209003215434, "grad_norm": 9.17254667692124, "learning_rate": 8.998367085662908e-06, "loss": 2.5076744556427, "step": 267 }, { "epoch": 0.8617363344051447, "grad_norm": 10.593922036651545, "learning_rate": 8.987097586955276e-06, "loss": 2.7998993396759033, "step": 268 }, { "epoch": 0.864951768488746, "grad_norm": 14.910537978617421, "learning_rate": 8.97577218562517e-06, "loss": 2.735177755355835, "step": 269 }, { "epoch": 0.8681672025723473, "grad_norm": 7.437460777250785, "learning_rate": 8.964391040464699e-06, "loss": 2.8440442085266113, "step": 270 }, { "epoch": 0.8713826366559485, "grad_norm": 9.856724829654736, "learning_rate": 8.952954311047554e-06, "loss": 3.18597674369812, "step": 271 }, { "epoch": 0.8745980707395499, "grad_norm": 12.798619966866845, "learning_rate": 8.941462157726757e-06, "loss": 2.6696226596832275, "step": 272 }, { "epoch": 0.8778135048231511, "grad_norm": 10.558246728168221, "learning_rate": 8.92991474163243e-06, "loss": 3.1313624382019043, "step": 273 }, { "epoch": 0.8810289389067524, "grad_norm": 73.1769401363515, "learning_rate": 8.918312224669523e-06, "loss": 2.7278852462768555, "step": 274 }, { "epoch": 0.8842443729903537, "grad_norm": 14.250721035805938, "learning_rate": 8.906654769515551e-06, "loss": 3.123018264770508, "step": 275 }, { "epoch": 0.887459807073955, "grad_norm": 13.624305251997455, "learning_rate": 8.89494253961831e-06, "loss": 2.5999131202697754, "step": 276 }, { "epoch": 0.8906752411575563, "grad_norm": 7.8025103094357, "learning_rate": 8.883175699193589e-06, "loss": 3.3754043579101562, "step": 277 }, { "epoch": 0.8938906752411575, "grad_norm": 14.813200674717987, "learning_rate": 8.871354413222859e-06, "loss": 2.477343797683716, "step": 278 }, { "epoch": 0.8971061093247589, "grad_norm": 16.927933274503733, "learning_rate": 8.85947884745097e-06, "loss": 3.132758140563965, "step": 279 }, { "epoch": 0.9003215434083601, "grad_norm": 7.191780346342989, "learning_rate": 8.847549168383823e-06, "loss": 2.820451021194458, "step": 280 }, { "epoch": 0.9035369774919614, "grad_norm": 8.389707727309089, "learning_rate": 8.835565543286031e-06, "loss": 2.6014206409454346, "step": 281 }, { "epoch": 0.9067524115755627, "grad_norm": 11.378077478241833, "learning_rate": 8.82352814017858e-06, "loss": 2.541848659515381, "step": 282 }, { "epoch": 0.909967845659164, "grad_norm": 8.237217625528718, "learning_rate": 8.811437127836477e-06, "loss": 2.961427688598633, "step": 283 }, { "epoch": 0.9131832797427653, "grad_norm": 14.816053043362626, "learning_rate": 8.799292675786365e-06, "loss": 2.8450682163238525, "step": 284 }, { "epoch": 0.9163987138263665, "grad_norm": 16.057064979343828, "learning_rate": 8.787094954304172e-06, "loss": 3.3827338218688965, "step": 285 }, { "epoch": 0.9196141479099679, "grad_norm": 10.580135043478649, "learning_rate": 8.7748441344127e-06, "loss": 2.749037265777588, "step": 286 }, { "epoch": 0.9228295819935691, "grad_norm": 13.251352277326397, "learning_rate": 8.762540387879245e-06, "loss": 2.7875254154205322, "step": 287 }, { "epoch": 0.9260450160771704, "grad_norm": 12.609710642983892, "learning_rate": 8.75018388721318e-06, "loss": 2.7887279987335205, "step": 288 }, { "epoch": 0.9292604501607717, "grad_norm": 14.143996593057057, "learning_rate": 8.73777480566353e-06, "loss": 3.5317232608795166, "step": 289 }, { "epoch": 0.932475884244373, "grad_norm": 10.953951580514532, "learning_rate": 8.725313317216558e-06, "loss": 2.695559024810791, "step": 290 }, { "epoch": 0.9356913183279743, "grad_norm": 19.652789221795818, "learning_rate": 8.712799596593317e-06, "loss": 3.773618698120117, "step": 291 }, { "epoch": 0.9389067524115756, "grad_norm": 28.646917195900233, "learning_rate": 8.7002338192472e-06, "loss": 2.8618407249450684, "step": 292 }, { "epoch": 0.9421221864951769, "grad_norm": 14.650325645648199, "learning_rate": 8.68761616136148e-06, "loss": 2.663022518157959, "step": 293 }, { "epoch": 0.9453376205787781, "grad_norm": 14.205451486366611, "learning_rate": 8.674946799846844e-06, "loss": 2.731468677520752, "step": 294 }, { "epoch": 0.9485530546623794, "grad_norm": 12.68853285402269, "learning_rate": 8.662225912338906e-06, "loss": 3.047337293624878, "step": 295 }, { "epoch": 0.9517684887459807, "grad_norm": 9.93366549634143, "learning_rate": 8.64945367719572e-06, "loss": 2.7521162033081055, "step": 296 }, { "epoch": 0.954983922829582, "grad_norm": 9.799333221523396, "learning_rate": 8.636630273495284e-06, "loss": 2.8862874507904053, "step": 297 }, { "epoch": 0.9581993569131833, "grad_norm": 9.853206555821423, "learning_rate": 8.623755881033016e-06, "loss": 2.4406180381774902, "step": 298 }, { "epoch": 0.9614147909967846, "grad_norm": 15.424788267085962, "learning_rate": 8.61083068031925e-06, "loss": 2.9202933311462402, "step": 299 }, { "epoch": 0.9646302250803859, "grad_norm": 8.470590376610176, "learning_rate": 8.59785485257669e-06, "loss": 2.7283151149749756, "step": 300 }, { "epoch": 0.9678456591639871, "grad_norm": 11.638302591399707, "learning_rate": 8.58482857973788e-06, "loss": 3.007424831390381, "step": 301 }, { "epoch": 0.9710610932475884, "grad_norm": 20.741792977624527, "learning_rate": 8.571752044442645e-06, "loss": 3.5147528648376465, "step": 302 }, { "epoch": 0.9742765273311897, "grad_norm": 13.142922472996343, "learning_rate": 8.558625430035537e-06, "loss": 2.6513309478759766, "step": 303 }, { "epoch": 0.977491961414791, "grad_norm": 16.4573242676752, "learning_rate": 8.54544892056326e-06, "loss": 2.8666458129882812, "step": 304 }, { "epoch": 0.9807073954983923, "grad_norm": 11.252470074853187, "learning_rate": 8.53222270077209e-06, "loss": 3.155954360961914, "step": 305 }, { "epoch": 0.9839228295819936, "grad_norm": 9.53791139505571, "learning_rate": 8.518946956105288e-06, "loss": 2.705427646636963, "step": 306 }, { "epoch": 0.9871382636655949, "grad_norm": 8.995699850871455, "learning_rate": 8.505621872700493e-06, "loss": 2.7899868488311768, "step": 307 }, { "epoch": 0.9903536977491961, "grad_norm": 20.466444028142707, "learning_rate": 8.492247637387123e-06, "loss": 3.3897032737731934, "step": 308 }, { "epoch": 0.9935691318327974, "grad_norm": 24.429378092820443, "learning_rate": 8.478824437683742e-06, "loss": 2.9029016494750977, "step": 309 }, { "epoch": 0.9967845659163987, "grad_norm": 14.9356195741505, "learning_rate": 8.465352461795443e-06, "loss": 2.8247499465942383, "step": 310 }, { "epoch": 1.0, "grad_norm": 6.9393031111913785, "learning_rate": 8.451831898611202e-06, "loss": 1.8072712421417236, "step": 311 }, { "epoch": 1.0032154340836013, "grad_norm": 15.619600920043508, "learning_rate": 8.438262937701232e-06, "loss": 1.6938456296920776, "step": 312 }, { "epoch": 1.0064308681672025, "grad_norm": 11.204028481476685, "learning_rate": 8.424645769314324e-06, "loss": 1.7548950910568237, "step": 313 }, { "epoch": 1.0096463022508038, "grad_norm": 11.12284902940604, "learning_rate": 8.410980584375184e-06, "loss": 1.2501029968261719, "step": 314 }, { "epoch": 1.0128617363344052, "grad_norm": 15.282718019978093, "learning_rate": 8.397267574481746e-06, "loss": 1.7188260555267334, "step": 315 }, { "epoch": 1.0160771704180065, "grad_norm": 21.75639670646837, "learning_rate": 8.3835069319025e-06, "loss": 1.522129774093628, "step": 316 }, { "epoch": 1.0192926045016077, "grad_norm": 24.92647139454926, "learning_rate": 8.369698849573778e-06, "loss": 1.9183681011199951, "step": 317 }, { "epoch": 1.022508038585209, "grad_norm": 12.732330001189787, "learning_rate": 8.355843521097071e-06, "loss": 1.1024775505065918, "step": 318 }, { "epoch": 1.0257234726688103, "grad_norm": 10.813488074904523, "learning_rate": 8.341941140736292e-06, "loss": 1.8346397876739502, "step": 319 }, { "epoch": 1.0289389067524115, "grad_norm": 13.745993996373599, "learning_rate": 8.327991903415071e-06, "loss": 1.5781948566436768, "step": 320 }, { "epoch": 1.0321543408360128, "grad_norm": 10.618379447829842, "learning_rate": 8.313996004714007e-06, "loss": 2.0449671745300293, "step": 321 }, { "epoch": 1.0353697749196142, "grad_norm": 30.15610599886493, "learning_rate": 8.29995364086794e-06, "loss": 1.843071460723877, "step": 322 }, { "epoch": 1.0385852090032155, "grad_norm": 11.641323891727778, "learning_rate": 8.285865008763185e-06, "loss": 1.9475151300430298, "step": 323 }, { "epoch": 1.0418006430868167, "grad_norm": 10.055339873855122, "learning_rate": 8.271730305934781e-06, "loss": 1.6771236658096313, "step": 324 }, { "epoch": 1.045016077170418, "grad_norm": 19.242811918496102, "learning_rate": 8.257549730563726e-06, "loss": 1.799647331237793, "step": 325 }, { "epoch": 1.0482315112540193, "grad_norm": 9.640296031149678, "learning_rate": 8.24332348147418e-06, "loss": 1.5140706300735474, "step": 326 }, { "epoch": 1.0514469453376205, "grad_norm": 17.52024512085222, "learning_rate": 8.229051758130697e-06, "loss": 1.7540702819824219, "step": 327 }, { "epoch": 1.0546623794212218, "grad_norm": 12.09956162787055, "learning_rate": 8.214734760635418e-06, "loss": 1.0229500532150269, "step": 328 }, { "epoch": 1.0578778135048232, "grad_norm": 9.27508841346202, "learning_rate": 8.200372689725265e-06, "loss": 1.9475460052490234, "step": 329 }, { "epoch": 1.0610932475884245, "grad_norm": 19.21666339915877, "learning_rate": 8.185965746769134e-06, "loss": 1.4429758787155151, "step": 330 }, { "epoch": 1.0643086816720257, "grad_norm": 13.399563404218933, "learning_rate": 8.171514133765062e-06, "loss": 2.7338225841522217, "step": 331 }, { "epoch": 1.067524115755627, "grad_norm": 13.76033185328455, "learning_rate": 8.157018053337401e-06, "loss": 2.250379800796509, "step": 332 }, { "epoch": 1.0707395498392283, "grad_norm": 7.631778726340121, "learning_rate": 8.142477708733977e-06, "loss": 1.337722659111023, "step": 333 }, { "epoch": 1.0739549839228295, "grad_norm": 13.880528130342933, "learning_rate": 8.127893303823237e-06, "loss": 1.0721861124038696, "step": 334 }, { "epoch": 1.077170418006431, "grad_norm": 12.862974801515321, "learning_rate": 8.113265043091393e-06, "loss": 1.4026358127593994, "step": 335 }, { "epoch": 1.0803858520900322, "grad_norm": 9.49382053942382, "learning_rate": 8.098593131639555e-06, "loss": 1.9554322957992554, "step": 336 }, { "epoch": 1.0836012861736335, "grad_norm": 9.28245720635116, "learning_rate": 8.083877775180851e-06, "loss": 1.3829636573791504, "step": 337 }, { "epoch": 1.0868167202572347, "grad_norm": 9.50422506559844, "learning_rate": 8.06911918003755e-06, "loss": 1.4771521091461182, "step": 338 }, { "epoch": 1.090032154340836, "grad_norm": 14.885902266047808, "learning_rate": 8.054317553138164e-06, "loss": 1.9953043460845947, "step": 339 }, { "epoch": 1.0932475884244373, "grad_norm": 21.84891512532416, "learning_rate": 8.039473102014552e-06, "loss": 1.8568346500396729, "step": 340 }, { "epoch": 1.0964630225080385, "grad_norm": 10.983885337102643, "learning_rate": 8.024586034798998e-06, "loss": 1.0092703104019165, "step": 341 }, { "epoch": 1.09967845659164, "grad_norm": 9.853494378778448, "learning_rate": 8.00965656022131e-06, "loss": 1.3574286699295044, "step": 342 }, { "epoch": 1.1028938906752412, "grad_norm": 9.677987937855264, "learning_rate": 7.994684887605877e-06, "loss": 1.5812814235687256, "step": 343 }, { "epoch": 1.1061093247588425, "grad_norm": 12.943696081924468, "learning_rate": 7.97967122686875e-06, "loss": 1.5962257385253906, "step": 344 }, { "epoch": 1.1093247588424437, "grad_norm": 11.101835108804991, "learning_rate": 7.964615788514683e-06, "loss": 1.9959800243377686, "step": 345 }, { "epoch": 1.112540192926045, "grad_norm": 9.080973101963357, "learning_rate": 7.949518783634191e-06, "loss": 1.4967670440673828, "step": 346 }, { "epoch": 1.1157556270096463, "grad_norm": 13.434521540385626, "learning_rate": 7.934380423900591e-06, "loss": 1.5423383712768555, "step": 347 }, { "epoch": 1.1189710610932475, "grad_norm": 10.76431702775392, "learning_rate": 7.919200921567029e-06, "loss": 0.7710652351379395, "step": 348 }, { "epoch": 1.122186495176849, "grad_norm": 9.814715538896447, "learning_rate": 7.903980489463507e-06, "loss": 1.6633532047271729, "step": 349 }, { "epoch": 1.1254019292604502, "grad_norm": 19.545538078520554, "learning_rate": 7.8887193409939e-06, "loss": 2.7766261100769043, "step": 350 }, { "epoch": 1.1286173633440515, "grad_norm": 9.41961139939792, "learning_rate": 7.87341769013296e-06, "loss": 1.6282963752746582, "step": 351 }, { "epoch": 1.1318327974276527, "grad_norm": 21.731938311350465, "learning_rate": 7.858075751423319e-06, "loss": 1.9692919254302979, "step": 352 }, { "epoch": 1.135048231511254, "grad_norm": 16.44935380857812, "learning_rate": 7.84269373997248e-06, "loss": 1.912774682044983, "step": 353 }, { "epoch": 1.1382636655948553, "grad_norm": 13.72564993302605, "learning_rate": 7.827271871449803e-06, "loss": 1.8513641357421875, "step": 354 }, { "epoch": 1.1414790996784565, "grad_norm": 14.127395536555673, "learning_rate": 7.811810362083476e-06, "loss": 1.7648791074752808, "step": 355 }, { "epoch": 1.144694533762058, "grad_norm": 11.466500120151354, "learning_rate": 7.79630942865749e-06, "loss": 1.8777326345443726, "step": 356 }, { "epoch": 1.1479099678456592, "grad_norm": 16.23925105600561, "learning_rate": 7.780769288508594e-06, "loss": 1.4060571193695068, "step": 357 }, { "epoch": 1.1511254019292605, "grad_norm": 13.429215394228326, "learning_rate": 7.76519015952325e-06, "loss": 1.8052624464035034, "step": 358 }, { "epoch": 1.1543408360128617, "grad_norm": 11.074667268910995, "learning_rate": 7.749572260134578e-06, "loss": 1.251237392425537, "step": 359 }, { "epoch": 1.157556270096463, "grad_norm": 9.520190196974967, "learning_rate": 7.733915809319295e-06, "loss": 1.7426929473876953, "step": 360 }, { "epoch": 1.1607717041800643, "grad_norm": 13.259610020931154, "learning_rate": 7.718221026594638e-06, "loss": 1.3306620121002197, "step": 361 }, { "epoch": 1.1639871382636655, "grad_norm": 11.55865396171068, "learning_rate": 7.7024881320153e-06, "loss": 1.1201272010803223, "step": 362 }, { "epoch": 1.167202572347267, "grad_norm": 18.047432249398582, "learning_rate": 7.686717346170323e-06, "loss": 1.2232224941253662, "step": 363 }, { "epoch": 1.1704180064308682, "grad_norm": 19.950356361520544, "learning_rate": 7.67090889018003e-06, "loss": 1.5430934429168701, "step": 364 }, { "epoch": 1.1736334405144695, "grad_norm": 11.821218809655774, "learning_rate": 7.655062985692905e-06, "loss": 1.1287882328033447, "step": 365 }, { "epoch": 1.1768488745980707, "grad_norm": 16.3870537176483, "learning_rate": 7.639179854882499e-06, "loss": 1.8235803842544556, "step": 366 }, { "epoch": 1.180064308681672, "grad_norm": 12.215851800288341, "learning_rate": 7.623259720444305e-06, "loss": 1.5709896087646484, "step": 367 }, { "epoch": 1.1832797427652733, "grad_norm": 10.179196448113856, "learning_rate": 7.6073028055926375e-06, "loss": 1.3701753616333008, "step": 368 }, { "epoch": 1.1864951768488745, "grad_norm": 13.266482945914282, "learning_rate": 7.591309334057511e-06, "loss": 1.8047711849212646, "step": 369 }, { "epoch": 1.189710610932476, "grad_norm": 12.558221362384941, "learning_rate": 7.5752795300814915e-06, "loss": 1.3536028861999512, "step": 370 }, { "epoch": 1.1929260450160772, "grad_norm": 8.288395487014714, "learning_rate": 7.5592136184165586e-06, "loss": 1.7526684999465942, "step": 371 }, { "epoch": 1.1961414790996785, "grad_norm": 32.312646691375775, "learning_rate": 7.543111824320956e-06, "loss": 1.9506163597106934, "step": 372 }, { "epoch": 1.1993569131832797, "grad_norm": 18.190358055738578, "learning_rate": 7.526974373556031e-06, "loss": 1.4558610916137695, "step": 373 }, { "epoch": 1.202572347266881, "grad_norm": 22.456941575166663, "learning_rate": 7.510801492383064e-06, "loss": 3.8982784748077393, "step": 374 }, { "epoch": 1.2057877813504823, "grad_norm": 9.286565530142028, "learning_rate": 7.494593407560105e-06, "loss": 1.4054985046386719, "step": 375 }, { "epoch": 1.2090032154340835, "grad_norm": 8.57272869781517, "learning_rate": 7.4783503463387915e-06, "loss": 1.4290287494659424, "step": 376 }, { "epoch": 1.212218649517685, "grad_norm": 25.62750132146527, "learning_rate": 7.462072536461158e-06, "loss": 2.6208114624023438, "step": 377 }, { "epoch": 1.2154340836012862, "grad_norm": 29.086655268807295, "learning_rate": 7.445760206156443e-06, "loss": 1.4879982471466064, "step": 378 }, { "epoch": 1.2186495176848875, "grad_norm": 10.92323075616016, "learning_rate": 7.429413584137899e-06, "loss": 1.5636539459228516, "step": 379 }, { "epoch": 1.2218649517684887, "grad_norm": 131.58390317452395, "learning_rate": 7.413032899599575e-06, "loss": 2.5596606731414795, "step": 380 }, { "epoch": 1.22508038585209, "grad_norm": 10.911077112816377, "learning_rate": 7.3966183822131055e-06, "loss": 1.7480653524398804, "step": 381 }, { "epoch": 1.2282958199356913, "grad_norm": 14.750459586463144, "learning_rate": 7.380170262124491e-06, "loss": 1.1983137130737305, "step": 382 }, { "epoch": 1.2315112540192925, "grad_norm": 10.193526385520498, "learning_rate": 7.363688769950874e-06, "loss": 2.4147493839263916, "step": 383 }, { "epoch": 1.234726688102894, "grad_norm": 8.110765389360624, "learning_rate": 7.347174136777303e-06, "loss": 1.5930522680282593, "step": 384 }, { "epoch": 1.2379421221864952, "grad_norm": 13.379838012098837, "learning_rate": 7.33062659415349e-06, "loss": 1.545811414718628, "step": 385 }, { "epoch": 1.2411575562700965, "grad_norm": 12.491186334322332, "learning_rate": 7.314046374090569e-06, "loss": 1.4453141689300537, "step": 386 }, { "epoch": 1.2443729903536977, "grad_norm": 11.673353502682332, "learning_rate": 7.297433709057837e-06, "loss": 1.6127538681030273, "step": 387 }, { "epoch": 1.247588424437299, "grad_norm": 14.231888382187387, "learning_rate": 7.280788831979504e-06, "loss": 1.3530693054199219, "step": 388 }, { "epoch": 1.2508038585209003, "grad_norm": 8.015144095452492, "learning_rate": 7.264111976231416e-06, "loss": 2.167546510696411, "step": 389 }, { "epoch": 1.2540192926045015, "grad_norm": 6.8301669716274125, "learning_rate": 7.247403375637789e-06, "loss": 1.1884214878082275, "step": 390 }, { "epoch": 1.257234726688103, "grad_norm": 9.740309887687731, "learning_rate": 7.230663264467932e-06, "loss": 1.8475289344787598, "step": 391 }, { "epoch": 1.2604501607717042, "grad_norm": 15.839480265530513, "learning_rate": 7.213891877432957e-06, "loss": 1.3596510887145996, "step": 392 }, { "epoch": 1.2636655948553055, "grad_norm": 8.14484618288492, "learning_rate": 7.197089449682495e-06, "loss": 1.1813664436340332, "step": 393 }, { "epoch": 1.2668810289389068, "grad_norm": 14.070099542557305, "learning_rate": 7.180256216801392e-06, "loss": 1.5710866451263428, "step": 394 }, { "epoch": 1.270096463022508, "grad_norm": 11.220505541098138, "learning_rate": 7.163392414806409e-06, "loss": 1.1523092985153198, "step": 395 }, { "epoch": 1.2733118971061093, "grad_norm": 9.667370363546029, "learning_rate": 7.146498280142917e-06, "loss": 1.584272861480713, "step": 396 }, { "epoch": 1.2765273311897105, "grad_norm": 7.714526098855273, "learning_rate": 7.1295740496815715e-06, "loss": 1.8063056468963623, "step": 397 }, { "epoch": 1.279742765273312, "grad_norm": 10.787378083877842, "learning_rate": 7.112619960715004e-06, "loss": 1.792249083518982, "step": 398 }, { "epoch": 1.2829581993569132, "grad_norm": 13.233918817558243, "learning_rate": 7.095636250954481e-06, "loss": 1.5670925378799438, "step": 399 }, { "epoch": 1.2861736334405145, "grad_norm": 11.79576476009515, "learning_rate": 7.078623158526588e-06, "loss": 0.8326504230499268, "step": 400 }, { "epoch": 1.2893890675241158, "grad_norm": 10.491299911652822, "learning_rate": 7.061580921969875e-06, "loss": 1.3786863088607788, "step": 401 }, { "epoch": 1.292604501607717, "grad_norm": 11.94691709161536, "learning_rate": 7.044509780231517e-06, "loss": 1.1054686307907104, "step": 402 }, { "epoch": 1.2958199356913183, "grad_norm": 12.08443122924739, "learning_rate": 7.027409972663972e-06, "loss": 1.670744776725769, "step": 403 }, { "epoch": 1.2990353697749195, "grad_norm": 12.818583379341405, "learning_rate": 7.010281739021612e-06, "loss": 1.4025758504867554, "step": 404 }, { "epoch": 1.302250803858521, "grad_norm": 17.63344093685557, "learning_rate": 6.993125319457371e-06, "loss": 1.3583598136901855, "step": 405 }, { "epoch": 1.3054662379421222, "grad_norm": 11.894949620821711, "learning_rate": 6.975940954519372e-06, "loss": 1.1004712581634521, "step": 406 }, { "epoch": 1.3086816720257235, "grad_norm": 12.892080489602101, "learning_rate": 6.958728885147559e-06, "loss": 1.2955303192138672, "step": 407 }, { "epoch": 1.3118971061093248, "grad_norm": 19.36393889877359, "learning_rate": 6.941489352670315e-06, "loss": 1.0670486688613892, "step": 408 }, { "epoch": 1.315112540192926, "grad_norm": 8.211056728192768, "learning_rate": 6.92422259880108e-06, "loss": 1.9638640880584717, "step": 409 }, { "epoch": 1.3183279742765273, "grad_norm": 10.833159131088287, "learning_rate": 6.9069288656349654e-06, "loss": 1.5076138973236084, "step": 410 }, { "epoch": 1.3215434083601285, "grad_norm": 8.58513007343669, "learning_rate": 6.8896083956453495e-06, "loss": 1.0038764476776123, "step": 411 }, { "epoch": 1.32475884244373, "grad_norm": 10.831768155951462, "learning_rate": 6.87226143168049e-06, "loss": 1.8994210958480835, "step": 412 }, { "epoch": 1.3279742765273312, "grad_norm": 9.967816587412674, "learning_rate": 6.8548882169601125e-06, "loss": 1.7425453662872314, "step": 413 }, { "epoch": 1.3311897106109325, "grad_norm": 11.573652006078895, "learning_rate": 6.837488995071999e-06, "loss": 0.9079417586326599, "step": 414 }, { "epoch": 1.3344051446945338, "grad_norm": 11.435087576974311, "learning_rate": 6.820064009968577e-06, "loss": 2.3625776767730713, "step": 415 }, { "epoch": 1.337620578778135, "grad_norm": 11.687306169218841, "learning_rate": 6.802613505963496e-06, "loss": 1.4717687368392944, "step": 416 }, { "epoch": 1.3408360128617363, "grad_norm": 7.907999407954611, "learning_rate": 6.7851377277282025e-06, "loss": 1.8274226188659668, "step": 417 }, { "epoch": 1.3440514469453375, "grad_norm": 13.33807600903979, "learning_rate": 6.767636920288514e-06, "loss": 0.9393669366836548, "step": 418 }, { "epoch": 1.347266881028939, "grad_norm": 18.07910651280989, "learning_rate": 6.7501113290211715e-06, "loss": 2.2995893955230713, "step": 419 }, { "epoch": 1.3504823151125402, "grad_norm": 13.219145457947517, "learning_rate": 6.732561199650417e-06, "loss": 0.9605876207351685, "step": 420 }, { "epoch": 1.3536977491961415, "grad_norm": 9.84083040492843, "learning_rate": 6.71498677824453e-06, "loss": 1.400538682937622, "step": 421 }, { "epoch": 1.3569131832797428, "grad_norm": 8.770195722914984, "learning_rate": 6.69738831121239e-06, "loss": 1.5933213233947754, "step": 422 }, { "epoch": 1.360128617363344, "grad_norm": 13.726188714507023, "learning_rate": 6.679766045300017e-06, "loss": 1.3214967250823975, "step": 423 }, { "epoch": 1.3633440514469453, "grad_norm": 11.733403335264603, "learning_rate": 6.66212022758711e-06, "loss": 1.8377995491027832, "step": 424 }, { "epoch": 1.3665594855305465, "grad_norm": 10.482810176903879, "learning_rate": 6.644451105483588e-06, "loss": 2.171910047531128, "step": 425 }, { "epoch": 1.369774919614148, "grad_norm": 10.272158746941752, "learning_rate": 6.626758926726118e-06, "loss": 1.01298987865448, "step": 426 }, { "epoch": 1.3729903536977492, "grad_norm": 10.850492383150184, "learning_rate": 6.609043939374638e-06, "loss": 1.3563112020492554, "step": 427 }, { "epoch": 1.3762057877813505, "grad_norm": 9.52772114565326, "learning_rate": 6.591306391808886e-06, "loss": 1.1524646282196045, "step": 428 }, { "epoch": 1.3794212218649518, "grad_norm": 9.634527311630647, "learning_rate": 6.5735465327249125e-06, "loss": 1.288474202156067, "step": 429 }, { "epoch": 1.382636655948553, "grad_norm": 15.933483184745002, "learning_rate": 6.555764611131599e-06, "loss": 1.6986860036849976, "step": 430 }, { "epoch": 1.3858520900321543, "grad_norm": 12.386422766725826, "learning_rate": 6.537960876347155e-06, "loss": 1.1839923858642578, "step": 431 }, { "epoch": 1.3890675241157555, "grad_norm": 10.253938139276935, "learning_rate": 6.520135577995636e-06, "loss": 1.0426067113876343, "step": 432 }, { "epoch": 1.392282958199357, "grad_norm": 11.04901140382035, "learning_rate": 6.502288966003437e-06, "loss": 1.5624547004699707, "step": 433 }, { "epoch": 1.3954983922829582, "grad_norm": 11.25738538359911, "learning_rate": 6.48442129059579e-06, "loss": 1.6425249576568604, "step": 434 }, { "epoch": 1.3987138263665595, "grad_norm": 7.369100897838746, "learning_rate": 6.4665328022932505e-06, "loss": 1.1195060014724731, "step": 435 }, { "epoch": 1.4019292604501608, "grad_norm": 8.920734482221718, "learning_rate": 6.448623751908193e-06, "loss": 1.9613807201385498, "step": 436 }, { "epoch": 1.405144694533762, "grad_norm": 17.2717195962134, "learning_rate": 6.43069439054129e-06, "loss": 1.9818463325500488, "step": 437 }, { "epoch": 1.4083601286173635, "grad_norm": 10.291894233810238, "learning_rate": 6.4127449695779894e-06, "loss": 1.321189284324646, "step": 438 }, { "epoch": 1.4115755627009645, "grad_norm": 14.652832324526607, "learning_rate": 6.394775740684996e-06, "loss": 1.653143048286438, "step": 439 }, { "epoch": 1.414790996784566, "grad_norm": 7.091089961179019, "learning_rate": 6.376786955806735e-06, "loss": 1.3114051818847656, "step": 440 }, { "epoch": 1.4180064308681672, "grad_norm": 8.725539866872378, "learning_rate": 6.358778867161829e-06, "loss": 1.6939886808395386, "step": 441 }, { "epoch": 1.4212218649517685, "grad_norm": 13.545006306769176, "learning_rate": 6.340751727239551e-06, "loss": 1.195266842842102, "step": 442 }, { "epoch": 1.4244372990353698, "grad_norm": 8.297440104157152, "learning_rate": 6.322705788796293e-06, "loss": 1.6877739429473877, "step": 443 }, { "epoch": 1.427652733118971, "grad_norm": 9.61755742164904, "learning_rate": 6.304641304852017e-06, "loss": 1.8234769105911255, "step": 444 }, { "epoch": 1.4308681672025725, "grad_norm": 8.53099814778349, "learning_rate": 6.286558528686713e-06, "loss": 1.707655429840088, "step": 445 }, { "epoch": 1.4340836012861735, "grad_norm": 16.09095041323655, "learning_rate": 6.268457713836839e-06, "loss": 1.685136318206787, "step": 446 }, { "epoch": 1.437299035369775, "grad_norm": 9.220851793207403, "learning_rate": 6.250339114091775e-06, "loss": 1.8174901008605957, "step": 447 }, { "epoch": 1.4405144694533762, "grad_norm": 16.91990210354561, "learning_rate": 6.2322029834902565e-06, "loss": 1.2479822635650635, "step": 448 }, { "epoch": 1.4437299035369775, "grad_norm": 18.222539873072662, "learning_rate": 6.214049576316824e-06, "loss": 2.1364529132843018, "step": 449 }, { "epoch": 1.4469453376205788, "grad_norm": 8.829662303717768, "learning_rate": 6.195879147098246e-06, "loss": 1.1708037853240967, "step": 450 }, { "epoch": 1.45016077170418, "grad_norm": 9.811681806402762, "learning_rate": 6.177691950599953e-06, "loss": 1.7463445663452148, "step": 451 }, { "epoch": 1.4533762057877815, "grad_norm": 15.76003868979169, "learning_rate": 6.159488241822473e-06, "loss": 1.4239546060562134, "step": 452 }, { "epoch": 1.4565916398713825, "grad_norm": 13.819031689596322, "learning_rate": 6.141268275997848e-06, "loss": 1.0984452962875366, "step": 453 }, { "epoch": 1.459807073954984, "grad_norm": 9.216205799504845, "learning_rate": 6.123032308586059e-06, "loss": 1.6430256366729736, "step": 454 }, { "epoch": 1.4630225080385852, "grad_norm": 12.706806062500931, "learning_rate": 6.10478059527144e-06, "loss": 1.4744967222213745, "step": 455 }, { "epoch": 1.4662379421221865, "grad_norm": 9.724752942795591, "learning_rate": 6.086513391959101e-06, "loss": 1.6440513134002686, "step": 456 }, { "epoch": 1.4694533762057878, "grad_norm": 12.12251316195964, "learning_rate": 6.068230954771334e-06, "loss": 1.4198493957519531, "step": 457 }, { "epoch": 1.472668810289389, "grad_norm": 10.329929581969795, "learning_rate": 6.0499335400440216e-06, "loss": 1.5990746021270752, "step": 458 }, { "epoch": 1.4758842443729905, "grad_norm": 18.5583606495554, "learning_rate": 6.031621404323046e-06, "loss": 1.1847198009490967, "step": 459 }, { "epoch": 1.4790996784565915, "grad_norm": 15.993991523648914, "learning_rate": 6.013294804360689e-06, "loss": 0.9134633541107178, "step": 460 }, { "epoch": 1.482315112540193, "grad_norm": 9.490813889864704, "learning_rate": 5.9949539971120405e-06, "loss": 2.0340170860290527, "step": 461 }, { "epoch": 1.4855305466237942, "grad_norm": 11.37889692680751, "learning_rate": 5.976599239731381e-06, "loss": 1.8881299495697021, "step": 462 }, { "epoch": 1.4887459807073955, "grad_norm": 9.569629046002419, "learning_rate": 5.9582307895685876e-06, "loss": 1.7137913703918457, "step": 463 }, { "epoch": 1.4919614147909968, "grad_norm": 12.420204461040186, "learning_rate": 5.939848904165519e-06, "loss": 1.2723381519317627, "step": 464 }, { "epoch": 1.495176848874598, "grad_norm": 11.926795629917983, "learning_rate": 5.9214538412524155e-06, "loss": 1.1736359596252441, "step": 465 }, { "epoch": 1.4983922829581995, "grad_norm": 12.405298290422278, "learning_rate": 5.903045858744271e-06, "loss": 1.3090627193450928, "step": 466 }, { "epoch": 1.5016077170418005, "grad_norm": 15.523116313387339, "learning_rate": 5.884625214737224e-06, "loss": 1.4756783246994019, "step": 467 }, { "epoch": 1.504823151125402, "grad_norm": 10.93229883191674, "learning_rate": 5.866192167504941e-06, "loss": 1.6622803211212158, "step": 468 }, { "epoch": 1.5080385852090032, "grad_norm": 17.915289620044277, "learning_rate": 5.84774697549499e-06, "loss": 1.6512175798416138, "step": 469 }, { "epoch": 1.5112540192926045, "grad_norm": 30.283483282050263, "learning_rate": 5.8292898973252246e-06, "loss": 1.4214634895324707, "step": 470 }, { "epoch": 1.5144694533762058, "grad_norm": 15.810670228159147, "learning_rate": 5.810821191780146e-06, "loss": 1.1714420318603516, "step": 471 }, { "epoch": 1.517684887459807, "grad_norm": 13.058805569793217, "learning_rate": 5.792341117807284e-06, "loss": 1.4205889701843262, "step": 472 }, { "epoch": 1.5209003215434085, "grad_norm": 10.022823791961894, "learning_rate": 5.773849934513568e-06, "loss": 1.419925570487976, "step": 473 }, { "epoch": 1.5241157556270095, "grad_norm": 12.48707482451956, "learning_rate": 5.755347901161683e-06, "loss": 1.8584307432174683, "step": 474 }, { "epoch": 1.527331189710611, "grad_norm": 12.857583603145283, "learning_rate": 5.736835277166446e-06, "loss": 2.2646093368530273, "step": 475 }, { "epoch": 1.5305466237942122, "grad_norm": 10.274067777361985, "learning_rate": 5.7183123220911615e-06, "loss": 0.9686712622642517, "step": 476 }, { "epoch": 1.5337620578778135, "grad_norm": 29.493341811852122, "learning_rate": 5.699779295643988e-06, "loss": 0.964187741279602, "step": 477 }, { "epoch": 1.5369774919614148, "grad_norm": 13.55003021738102, "learning_rate": 5.68123645767429e-06, "loss": 1.0403389930725098, "step": 478 }, { "epoch": 1.540192926045016, "grad_norm": 12.54908295885377, "learning_rate": 5.662684068169002e-06, "loss": 1.6527446508407593, "step": 479 }, { "epoch": 1.5434083601286175, "grad_norm": 6.610317425915739, "learning_rate": 5.644122387248975e-06, "loss": 1.4375754594802856, "step": 480 }, { "epoch": 1.5466237942122185, "grad_norm": 11.06854659241844, "learning_rate": 5.6255516751653376e-06, "loss": 1.3001888990402222, "step": 481 }, { "epoch": 1.54983922829582, "grad_norm": 21.599505542000774, "learning_rate": 5.606972192295841e-06, "loss": 1.9102635383605957, "step": 482 }, { "epoch": 1.5530546623794212, "grad_norm": 11.405842693936945, "learning_rate": 5.588384199141211e-06, "loss": 1.1081337928771973, "step": 483 }, { "epoch": 1.5562700964630225, "grad_norm": 10.182874123460897, "learning_rate": 5.569787956321496e-06, "loss": 1.2650421857833862, "step": 484 }, { "epoch": 1.5594855305466238, "grad_norm": 13.134492774505976, "learning_rate": 5.551183724572411e-06, "loss": 1.2185710668563843, "step": 485 }, { "epoch": 1.562700964630225, "grad_norm": 15.44354876414701, "learning_rate": 5.532571764741686e-06, "loss": 1.2483716011047363, "step": 486 }, { "epoch": 1.5659163987138265, "grad_norm": 13.467838369490899, "learning_rate": 5.513952337785398e-06, "loss": 1.7064783573150635, "step": 487 }, { "epoch": 1.5691318327974275, "grad_norm": 11.973440553832287, "learning_rate": 5.4953257047643284e-06, "loss": 1.9306564331054688, "step": 488 }, { "epoch": 1.572347266881029, "grad_norm": 12.222087950483303, "learning_rate": 5.476692126840287e-06, "loss": 1.796401858329773, "step": 489 }, { "epoch": 1.5755627009646302, "grad_norm": 14.251036373638994, "learning_rate": 5.458051865272462e-06, "loss": 1.9565566778182983, "step": 490 }, { "epoch": 1.5787781350482315, "grad_norm": 12.909098298317854, "learning_rate": 5.439405181413752e-06, "loss": 1.7262601852416992, "step": 491 }, { "epoch": 1.5819935691318328, "grad_norm": 9.663223095722376, "learning_rate": 5.420752336707098e-06, "loss": 1.2656997442245483, "step": 492 }, { "epoch": 1.585209003215434, "grad_norm": 15.520726456430584, "learning_rate": 5.402093592681823e-06, "loss": 1.3866935968399048, "step": 493 }, { "epoch": 1.5884244372990355, "grad_norm": 10.917894975556058, "learning_rate": 5.383429210949967e-06, "loss": 0.8932974934577942, "step": 494 }, { "epoch": 1.5916398713826365, "grad_norm": 13.277750253841756, "learning_rate": 5.36475945320261e-06, "loss": 1.5216851234436035, "step": 495 }, { "epoch": 1.594855305466238, "grad_norm": 12.30741363554072, "learning_rate": 5.346084581206215e-06, "loss": 1.0728681087493896, "step": 496 }, { "epoch": 1.5980707395498392, "grad_norm": 29.029933055790377, "learning_rate": 5.327404856798944e-06, "loss": 1.913758635520935, "step": 497 }, { "epoch": 1.6012861736334405, "grad_norm": 12.42781087693241, "learning_rate": 5.3087205418870014e-06, "loss": 1.6854526996612549, "step": 498 }, { "epoch": 1.6045016077170418, "grad_norm": 9.018921661705617, "learning_rate": 5.29003189844095e-06, "loss": 1.147437334060669, "step": 499 }, { "epoch": 1.607717041800643, "grad_norm": 13.581361587228178, "learning_rate": 5.2713391884920415e-06, "loss": 2.265592098236084, "step": 500 }, { "epoch": 1.6109324758842445, "grad_norm": 9.087003042899404, "learning_rate": 5.2526426741285465e-06, "loss": 1.6772857904434204, "step": 501 }, { "epoch": 1.6141479099678455, "grad_norm": 12.529074715254756, "learning_rate": 5.233942617492077e-06, "loss": 1.633618712425232, "step": 502 }, { "epoch": 1.617363344051447, "grad_norm": 12.64649957772085, "learning_rate": 5.215239280773908e-06, "loss": 1.5846664905548096, "step": 503 }, { "epoch": 1.6205787781350482, "grad_norm": 8.149292574594154, "learning_rate": 5.196532926211307e-06, "loss": 1.4743802547454834, "step": 504 }, { "epoch": 1.6237942122186495, "grad_norm": 30.942623906686798, "learning_rate": 5.177823816083853e-06, "loss": 1.7887756824493408, "step": 505 }, { "epoch": 1.6270096463022508, "grad_norm": 10.656347918532477, "learning_rate": 5.15911221270976e-06, "loss": 1.8924931287765503, "step": 506 }, { "epoch": 1.630225080385852, "grad_norm": 11.982264969959546, "learning_rate": 5.140398378442201e-06, "loss": 1.5837712287902832, "step": 507 }, { "epoch": 1.6334405144694535, "grad_norm": 17.74630841676715, "learning_rate": 5.121682575665625e-06, "loss": 1.3969013690948486, "step": 508 }, { "epoch": 1.6366559485530545, "grad_norm": 13.757379611481515, "learning_rate": 5.102965066792085e-06, "loss": 1.3699804544448853, "step": 509 }, { "epoch": 1.639871382636656, "grad_norm": 9.471724169843402, "learning_rate": 5.084246114257554e-06, "loss": 1.3550987243652344, "step": 510 }, { "epoch": 1.6430868167202572, "grad_norm": 15.596683071578276, "learning_rate": 5.065525980518244e-06, "loss": 1.2851953506469727, "step": 511 }, { "epoch": 1.6463022508038585, "grad_norm": 10.623931822433907, "learning_rate": 5.046804928046933e-06, "loss": 1.3243783712387085, "step": 512 }, { "epoch": 1.6495176848874598, "grad_norm": 22.19363105957551, "learning_rate": 5.028083219329274e-06, "loss": 1.6754820346832275, "step": 513 }, { "epoch": 1.652733118971061, "grad_norm": 10.186022632613163, "learning_rate": 5.009361116860129e-06, "loss": 2.1871590614318848, "step": 514 }, { "epoch": 1.6559485530546625, "grad_norm": 14.398718167356659, "learning_rate": 4.990638883139872e-06, "loss": 0.9794585108757019, "step": 515 }, { "epoch": 1.6591639871382635, "grad_norm": 10.294011417163757, "learning_rate": 4.9719167806707265e-06, "loss": 1.329102635383606, "step": 516 }, { "epoch": 1.662379421221865, "grad_norm": 10.782193417515709, "learning_rate": 4.953195071953069e-06, "loss": 1.4713919162750244, "step": 517 }, { "epoch": 1.6655948553054662, "grad_norm": 20.256749627414443, "learning_rate": 4.934474019481755e-06, "loss": 1.6331861019134521, "step": 518 }, { "epoch": 1.6688102893890675, "grad_norm": 10.326694785789037, "learning_rate": 4.915753885742446e-06, "loss": 0.8953830003738403, "step": 519 }, { "epoch": 1.6720257234726688, "grad_norm": 34.510915012884716, "learning_rate": 4.8970349332079155e-06, "loss": 2.0606470108032227, "step": 520 }, { "epoch": 1.67524115755627, "grad_norm": 22.26005680178925, "learning_rate": 4.8783174243343765e-06, "loss": 1.9117261171340942, "step": 521 }, { "epoch": 1.6784565916398715, "grad_norm": 11.981892440704723, "learning_rate": 4.8596016215578e-06, "loss": 1.107745885848999, "step": 522 }, { "epoch": 1.6816720257234725, "grad_norm": 7.902869741318056, "learning_rate": 4.8408877872902404e-06, "loss": 2.056065559387207, "step": 523 }, { "epoch": 1.684887459807074, "grad_norm": 14.657507529582745, "learning_rate": 4.822176183916147e-06, "loss": 1.2189289331436157, "step": 524 }, { "epoch": 1.6881028938906752, "grad_norm": 15.323149691380317, "learning_rate": 4.803467073788694e-06, "loss": 1.1678478717803955, "step": 525 }, { "epoch": 1.6913183279742765, "grad_norm": 10.369820938531406, "learning_rate": 4.7847607192260916e-06, "loss": 1.3617630004882812, "step": 526 }, { "epoch": 1.694533762057878, "grad_norm": 16.278666347716534, "learning_rate": 4.766057382507924e-06, "loss": 1.8124133348464966, "step": 527 }, { "epoch": 1.697749196141479, "grad_norm": 11.617355712233303, "learning_rate": 4.747357325871454e-06, "loss": 1.7624785900115967, "step": 528 }, { "epoch": 1.7009646302250805, "grad_norm": 6.976469169369697, "learning_rate": 4.72866081150796e-06, "loss": 1.804181456565857, "step": 529 }, { "epoch": 1.7041800643086815, "grad_norm": 8.884998817103593, "learning_rate": 4.709968101559051e-06, "loss": 1.8973114490509033, "step": 530 }, { "epoch": 1.707395498392283, "grad_norm": 10.671057224558174, "learning_rate": 4.6912794581129985e-06, "loss": 2.0870800018310547, "step": 531 }, { "epoch": 1.7106109324758842, "grad_norm": 10.490926549117916, "learning_rate": 4.672595143201056e-06, "loss": 1.4478678703308105, "step": 532 }, { "epoch": 1.7138263665594855, "grad_norm": 10.312387100131009, "learning_rate": 4.653915418793786e-06, "loss": 1.0462535619735718, "step": 533 }, { "epoch": 1.717041800643087, "grad_norm": 12.221086012098088, "learning_rate": 4.63524054679739e-06, "loss": 1.0799921751022339, "step": 534 }, { "epoch": 1.720257234726688, "grad_norm": 6.827983273847641, "learning_rate": 4.616570789050034e-06, "loss": 0.9600023031234741, "step": 535 }, { "epoch": 1.7234726688102895, "grad_norm": 8.94999117796044, "learning_rate": 4.5979064073181775e-06, "loss": 1.4467713832855225, "step": 536 }, { "epoch": 1.7266881028938905, "grad_norm": 11.947768679414317, "learning_rate": 4.579247663292903e-06, "loss": 1.1485623121261597, "step": 537 }, { "epoch": 1.729903536977492, "grad_norm": 7.738903631330294, "learning_rate": 4.560594818586248e-06, "loss": 1.881239891052246, "step": 538 }, { "epoch": 1.7331189710610932, "grad_norm": 14.43039125664941, "learning_rate": 4.541948134727538e-06, "loss": 1.4121603965759277, "step": 539 }, { "epoch": 1.7363344051446945, "grad_norm": 13.559187134442164, "learning_rate": 4.523307873159714e-06, "loss": 1.600027084350586, "step": 540 }, { "epoch": 1.739549839228296, "grad_norm": 12.924451068775486, "learning_rate": 4.504674295235673e-06, "loss": 1.9366849660873413, "step": 541 }, { "epoch": 1.742765273311897, "grad_norm": 10.348503628222995, "learning_rate": 4.486047662214602e-06, "loss": 1.147647500038147, "step": 542 }, { "epoch": 1.7459807073954985, "grad_norm": 9.22563519797577, "learning_rate": 4.467428235258315e-06, "loss": 2.267954111099243, "step": 543 }, { "epoch": 1.7491961414790995, "grad_norm": 11.921588194327418, "learning_rate": 4.448816275427589e-06, "loss": 1.3431754112243652, "step": 544 }, { "epoch": 1.752411575562701, "grad_norm": 13.456836651748802, "learning_rate": 4.430212043678506e-06, "loss": 1.371949553489685, "step": 545 }, { "epoch": 1.7556270096463023, "grad_norm": 11.31057602108461, "learning_rate": 4.41161580085879e-06, "loss": 1.2015950679779053, "step": 546 }, { "epoch": 1.7588424437299035, "grad_norm": 11.775227684435517, "learning_rate": 4.39302780770416e-06, "loss": 1.2269978523254395, "step": 547 }, { "epoch": 1.762057877813505, "grad_norm": 9.277512918356958, "learning_rate": 4.374448324834664e-06, "loss": 1.1524686813354492, "step": 548 }, { "epoch": 1.765273311897106, "grad_norm": 13.986012721095971, "learning_rate": 4.355877612751027e-06, "loss": 0.8838063478469849, "step": 549 }, { "epoch": 1.7684887459807075, "grad_norm": 9.61624989824511, "learning_rate": 4.337315931830999e-06, "loss": 1.0831339359283447, "step": 550 }, { "epoch": 1.7717041800643085, "grad_norm": 10.157468448463078, "learning_rate": 4.318763542325711e-06, "loss": 1.1000258922576904, "step": 551 }, { "epoch": 1.77491961414791, "grad_norm": 9.188155688035968, "learning_rate": 4.3002207043560135e-06, "loss": 1.230742335319519, "step": 552 }, { "epoch": 1.7781350482315113, "grad_norm": 9.615692013478174, "learning_rate": 4.28168767790884e-06, "loss": 1.103325605392456, "step": 553 }, { "epoch": 1.7813504823151125, "grad_norm": 8.302705452574013, "learning_rate": 4.263164722833556e-06, "loss": 1.3692865371704102, "step": 554 }, { "epoch": 1.784565916398714, "grad_norm": 14.643567177677879, "learning_rate": 4.2446520988383185e-06, "loss": 0.6936740875244141, "step": 555 }, { "epoch": 1.787781350482315, "grad_norm": 9.360894269774661, "learning_rate": 4.226150065486434e-06, "loss": 0.7901575565338135, "step": 556 }, { "epoch": 1.7909967845659165, "grad_norm": 12.472712807562056, "learning_rate": 4.207658882192717e-06, "loss": 1.3338205814361572, "step": 557 }, { "epoch": 1.7942122186495175, "grad_norm": 11.717589080001146, "learning_rate": 4.189178808219856e-06, "loss": 1.3363522291183472, "step": 558 }, { "epoch": 1.797427652733119, "grad_norm": 10.30067614909667, "learning_rate": 4.170710102674777e-06, "loss": 1.8522659540176392, "step": 559 }, { "epoch": 1.8006430868167203, "grad_norm": 9.820476935188125, "learning_rate": 4.152253024505011e-06, "loss": 1.9775140285491943, "step": 560 }, { "epoch": 1.8038585209003215, "grad_norm": 10.166187506670667, "learning_rate": 4.133807832495062e-06, "loss": 1.0015840530395508, "step": 561 }, { "epoch": 1.807073954983923, "grad_norm": 15.340234839194505, "learning_rate": 4.1153747852627775e-06, "loss": 1.753740906715393, "step": 562 }, { "epoch": 1.810289389067524, "grad_norm": 8.962676705869463, "learning_rate": 4.096954141255731e-06, "loss": 1.5827150344848633, "step": 563 }, { "epoch": 1.8135048231511255, "grad_norm": 15.147384411595603, "learning_rate": 4.078546158747586e-06, "loss": 0.916832685470581, "step": 564 }, { "epoch": 1.8167202572347267, "grad_norm": 10.569002234689366, "learning_rate": 4.060151095834482e-06, "loss": 1.4536582231521606, "step": 565 }, { "epoch": 1.819935691318328, "grad_norm": 9.415759397401844, "learning_rate": 4.041769210431414e-06, "loss": 1.4267023801803589, "step": 566 }, { "epoch": 1.8231511254019293, "grad_norm": 7.078102010311895, "learning_rate": 4.02340076026862e-06, "loss": 1.1329270601272583, "step": 567 }, { "epoch": 1.8263665594855305, "grad_norm": 10.876729484364853, "learning_rate": 4.00504600288796e-06, "loss": 1.7833589315414429, "step": 568 }, { "epoch": 1.829581993569132, "grad_norm": 13.635055310739693, "learning_rate": 3.9867051956393114e-06, "loss": 1.2976348400115967, "step": 569 }, { "epoch": 1.832797427652733, "grad_norm": 10.771584206810726, "learning_rate": 3.968378595676956e-06, "loss": 1.4629448652267456, "step": 570 }, { "epoch": 1.8360128617363345, "grad_norm": 11.703783804229115, "learning_rate": 3.95006645995598e-06, "loss": 2.5722076892852783, "step": 571 }, { "epoch": 1.8392282958199357, "grad_norm": 12.349504033741153, "learning_rate": 3.931769045228668e-06, "loss": 2.2091426849365234, "step": 572 }, { "epoch": 1.842443729903537, "grad_norm": 11.542335230955135, "learning_rate": 3.9134866080409e-06, "loss": 1.391589641571045, "step": 573 }, { "epoch": 1.8456591639871383, "grad_norm": 12.806637836059952, "learning_rate": 3.895219404728561e-06, "loss": 1.1414397954940796, "step": 574 }, { "epoch": 1.8488745980707395, "grad_norm": 14.264578459530476, "learning_rate": 3.8769676914139426e-06, "loss": 1.059516191482544, "step": 575 }, { "epoch": 1.852090032154341, "grad_norm": 19.271915274351503, "learning_rate": 3.858731724002153e-06, "loss": 2.1879444122314453, "step": 576 }, { "epoch": 1.855305466237942, "grad_norm": 12.309421348778711, "learning_rate": 3.840511758177528e-06, "loss": 1.473386526107788, "step": 577 }, { "epoch": 1.8585209003215435, "grad_norm": 10.878678959452348, "learning_rate": 3.822308049400047e-06, "loss": 1.4653959274291992, "step": 578 }, { "epoch": 1.8617363344051447, "grad_norm": 8.040534262037765, "learning_rate": 3.804120852901756e-06, "loss": 1.6413612365722656, "step": 579 }, { "epoch": 1.864951768488746, "grad_norm": 9.044916275419325, "learning_rate": 3.7859504236831766e-06, "loss": 1.316032886505127, "step": 580 }, { "epoch": 1.8681672025723473, "grad_norm": 14.730705685102624, "learning_rate": 3.7677970165097444e-06, "loss": 1.7361235618591309, "step": 581 }, { "epoch": 1.8713826366559485, "grad_norm": 7.6900213009486675, "learning_rate": 3.749660885908226e-06, "loss": 1.667905569076538, "step": 582 }, { "epoch": 1.87459807073955, "grad_norm": 11.07535258062379, "learning_rate": 3.7315422861631623e-06, "loss": 1.065222978591919, "step": 583 }, { "epoch": 1.877813504823151, "grad_norm": 8.326344701604272, "learning_rate": 3.7134414713132883e-06, "loss": 1.115635633468628, "step": 584 }, { "epoch": 1.8810289389067525, "grad_norm": 18.801864494350724, "learning_rate": 3.6953586951479834e-06, "loss": 2.2017221450805664, "step": 585 }, { "epoch": 1.8842443729903537, "grad_norm": 25.418633684284842, "learning_rate": 3.677294211203708e-06, "loss": 2.484564781188965, "step": 586 }, { "epoch": 1.887459807073955, "grad_norm": 12.423647444445745, "learning_rate": 3.6592482727604508e-06, "loss": 1.3357205390930176, "step": 587 }, { "epoch": 1.8906752411575563, "grad_norm": 12.144643827381929, "learning_rate": 3.641221132838173e-06, "loss": 1.3544979095458984, "step": 588 }, { "epoch": 1.8938906752411575, "grad_norm": 12.46311005742411, "learning_rate": 3.623213044193266e-06, "loss": 0.9614198207855225, "step": 589 }, { "epoch": 1.897106109324759, "grad_norm": 10.364954003308453, "learning_rate": 3.605224259315005e-06, "loss": 1.2620229721069336, "step": 590 }, { "epoch": 1.90032154340836, "grad_norm": 9.237871106266182, "learning_rate": 3.587255030422011e-06, "loss": 1.886639952659607, "step": 591 }, { "epoch": 1.9035369774919615, "grad_norm": 13.030874547511374, "learning_rate": 3.569305609458712e-06, "loss": 1.2755482196807861, "step": 592 }, { "epoch": 1.9067524115755627, "grad_norm": 11.110774284864801, "learning_rate": 3.5513762480918084e-06, "loss": 1.4138600826263428, "step": 593 }, { "epoch": 1.909967845659164, "grad_norm": 13.866814610623521, "learning_rate": 3.5334671977067504e-06, "loss": 1.2061731815338135, "step": 594 }, { "epoch": 1.9131832797427653, "grad_norm": 11.47086636607418, "learning_rate": 3.5155787094042113e-06, "loss": 1.641986608505249, "step": 595 }, { "epoch": 1.9163987138263665, "grad_norm": 12.881675239858552, "learning_rate": 3.497711033996564e-06, "loss": 1.2158643007278442, "step": 596 }, { "epoch": 1.919614147909968, "grad_norm": 10.830930409963317, "learning_rate": 3.4798644220043663e-06, "loss": 1.8701896667480469, "step": 597 }, { "epoch": 1.922829581993569, "grad_norm": 18.238087057780916, "learning_rate": 3.462039123652847e-06, "loss": 1.195351243019104, "step": 598 }, { "epoch": 1.9260450160771705, "grad_norm": 18.418356217668133, "learning_rate": 3.444235388868403e-06, "loss": 1.2579845190048218, "step": 599 }, { "epoch": 1.9292604501607717, "grad_norm": 12.58424302992326, "learning_rate": 3.4264534672750884e-06, "loss": 1.524860143661499, "step": 600 }, { "epoch": 1.932475884244373, "grad_norm": 8.098300750497785, "learning_rate": 3.408693608191116e-06, "loss": 1.286231517791748, "step": 601 }, { "epoch": 1.9356913183279743, "grad_norm": 9.863741692326508, "learning_rate": 3.3909560606253632e-06, "loss": 1.322242021560669, "step": 602 }, { "epoch": 1.9389067524115755, "grad_norm": 12.987443308520445, "learning_rate": 3.3732410732738843e-06, "loss": 1.4537055492401123, "step": 603 }, { "epoch": 1.942122186495177, "grad_norm": 10.506554610719009, "learning_rate": 3.3555488945164127e-06, "loss": 1.5410267114639282, "step": 604 }, { "epoch": 1.945337620578778, "grad_norm": 10.174939767346636, "learning_rate": 3.337879772412892e-06, "loss": 1.754872441291809, "step": 605 }, { "epoch": 1.9485530546623795, "grad_norm": 10.59532168962947, "learning_rate": 3.320233954699985e-06, "loss": 1.4205820560455322, "step": 606 }, { "epoch": 1.9517684887459807, "grad_norm": 25.622835260786083, "learning_rate": 3.302611688787612e-06, "loss": 1.73175048828125, "step": 607 }, { "epoch": 1.954983922829582, "grad_norm": 9.901036226861155, "learning_rate": 3.285013221755472e-06, "loss": 1.4618065357208252, "step": 608 }, { "epoch": 1.9581993569131833, "grad_norm": 13.405612432143831, "learning_rate": 3.267438800349586e-06, "loss": 1.0909953117370605, "step": 609 }, { "epoch": 1.9614147909967845, "grad_norm": 14.915858656289252, "learning_rate": 3.2498886709788298e-06, "loss": 1.2120417356491089, "step": 610 }, { "epoch": 1.964630225080386, "grad_norm": 11.503072772803362, "learning_rate": 3.2323630797114892e-06, "loss": 1.560947060585022, "step": 611 }, { "epoch": 1.967845659163987, "grad_norm": 13.493518918254455, "learning_rate": 3.214862272271799e-06, "loss": 1.1600837707519531, "step": 612 }, { "epoch": 1.9710610932475885, "grad_norm": 15.01023608928888, "learning_rate": 3.1973864940365076e-06, "loss": 1.0669816732406616, "step": 613 }, { "epoch": 1.9742765273311897, "grad_norm": 12.264629967700163, "learning_rate": 3.179935990031425e-06, "loss": 1.236401081085205, "step": 614 }, { "epoch": 1.977491961414791, "grad_norm": 12.416946892637084, "learning_rate": 3.162511004928003e-06, "loss": 0.8553851842880249, "step": 615 }, { "epoch": 1.9807073954983923, "grad_norm": 10.966787271475475, "learning_rate": 3.1451117830398896e-06, "loss": 1.6353504657745361, "step": 616 }, { "epoch": 1.9839228295819935, "grad_norm": 11.04503339220036, "learning_rate": 3.1277385683195117e-06, "loss": 1.8089317083358765, "step": 617 }, { "epoch": 1.987138263665595, "grad_norm": 16.458323320048635, "learning_rate": 3.110391604354652e-06, "loss": 1.1577980518341064, "step": 618 }, { "epoch": 1.990353697749196, "grad_norm": 16.20975999278611, "learning_rate": 3.093071134365037e-06, "loss": 2.4027674198150635, "step": 619 }, { "epoch": 1.9935691318327975, "grad_norm": 23.51251674539541, "learning_rate": 3.075777401198922e-06, "loss": 1.3853836059570312, "step": 620 }, { "epoch": 1.9967845659163987, "grad_norm": 8.708072763645559, "learning_rate": 3.058510647329688e-06, "loss": 2.743666410446167, "step": 621 }, { "epoch": 2.0, "grad_norm": 11.979852138626141, "learning_rate": 3.041271114852443e-06, "loss": 1.1549768447875977, "step": 622 }, { "epoch": 2.0032154340836015, "grad_norm": 14.314789124914883, "learning_rate": 3.02405904548063e-06, "loss": 1.0811271667480469, "step": 623 }, { "epoch": 2.0064308681672025, "grad_norm": 9.87321228153049, "learning_rate": 3.0068746805426318e-06, "loss": 0.35157322883605957, "step": 624 }, { "epoch": 2.009646302250804, "grad_norm": 9.320230936525673, "learning_rate": 2.9897182609783905e-06, "loss": 0.40260130167007446, "step": 625 }, { "epoch": 2.012861736334405, "grad_norm": 9.052307743678542, "learning_rate": 2.97259002733603e-06, "loss": 0.870284378528595, "step": 626 }, { "epoch": 2.0160771704180065, "grad_norm": 8.178905821906115, "learning_rate": 2.9554902197684843e-06, "loss": 0.4470030963420868, "step": 627 }, { "epoch": 2.0192926045016075, "grad_norm": 12.906748407694202, "learning_rate": 2.938419078030128e-06, "loss": 0.6769909858703613, "step": 628 }, { "epoch": 2.022508038585209, "grad_norm": 15.160992244136171, "learning_rate": 2.9213768414734146e-06, "loss": 0.5105010271072388, "step": 629 }, { "epoch": 2.0257234726688105, "grad_norm": 9.593795396914789, "learning_rate": 2.90436374904552e-06, "loss": 0.5568506121635437, "step": 630 }, { "epoch": 2.0289389067524115, "grad_norm": 8.019441658658858, "learning_rate": 2.887380039284999e-06, "loss": 0.21812975406646729, "step": 631 }, { "epoch": 2.032154340836013, "grad_norm": 7.294457920425058, "learning_rate": 2.8704259503184306e-06, "loss": 0.5240740776062012, "step": 632 }, { "epoch": 2.035369774919614, "grad_norm": 8.804193733481519, "learning_rate": 2.853501719857086e-06, "loss": 0.3466935455799103, "step": 633 }, { "epoch": 2.0385852090032155, "grad_norm": 10.734383468470607, "learning_rate": 2.8366075851935927e-06, "loss": 0.6415536403656006, "step": 634 }, { "epoch": 2.0418006430868165, "grad_norm": 7.475946116985285, "learning_rate": 2.8197437831986085e-06, "loss": 0.4148802161216736, "step": 635 }, { "epoch": 2.045016077170418, "grad_norm": 11.258686396792596, "learning_rate": 2.802910550317506e-06, "loss": 0.7162201404571533, "step": 636 }, { "epoch": 2.0482315112540195, "grad_norm": 9.209880063404333, "learning_rate": 2.786108122567044e-06, "loss": 0.5609467029571533, "step": 637 }, { "epoch": 2.0514469453376205, "grad_norm": 10.662055158233054, "learning_rate": 2.769336735532068e-06, "loss": 0.4859113395214081, "step": 638 }, { "epoch": 2.054662379421222, "grad_norm": 8.827327001805601, "learning_rate": 2.7525966243622105e-06, "loss": 0.35435792803764343, "step": 639 }, { "epoch": 2.057877813504823, "grad_norm": 8.027492720872965, "learning_rate": 2.7358880237685844e-06, "loss": 0.2768567204475403, "step": 640 }, { "epoch": 2.0610932475884245, "grad_norm": 10.207767409910922, "learning_rate": 2.7192111680204957e-06, "loss": 0.24898266792297363, "step": 641 }, { "epoch": 2.0643086816720255, "grad_norm": 9.78068569866971, "learning_rate": 2.7025662909421625e-06, "loss": 0.7269777059555054, "step": 642 }, { "epoch": 2.067524115755627, "grad_norm": 14.513005174422293, "learning_rate": 2.685953625909432e-06, "loss": 0.6724145412445068, "step": 643 }, { "epoch": 2.0707395498392285, "grad_norm": 12.097896199856809, "learning_rate": 2.6693734058465105e-06, "loss": 0.5692760348320007, "step": 644 }, { "epoch": 2.0739549839228295, "grad_norm": 13.857845362848131, "learning_rate": 2.652825863222698e-06, "loss": 0.5785061717033386, "step": 645 }, { "epoch": 2.077170418006431, "grad_norm": 9.786540455953286, "learning_rate": 2.636311230049125e-06, "loss": 0.3663535416126251, "step": 646 }, { "epoch": 2.080385852090032, "grad_norm": 12.912854147301195, "learning_rate": 2.619829737875509e-06, "loss": 0.4806700050830841, "step": 647 }, { "epoch": 2.0836012861736335, "grad_norm": 8.68661115707137, "learning_rate": 2.6033816177868954e-06, "loss": 0.5164961814880371, "step": 648 }, { "epoch": 2.0868167202572345, "grad_norm": 13.93536389564521, "learning_rate": 2.5869671004004256e-06, "loss": 0.6894420385360718, "step": 649 }, { "epoch": 2.090032154340836, "grad_norm": 7.225443037652673, "learning_rate": 2.5705864158621008e-06, "loss": 0.4011325538158417, "step": 650 }, { "epoch": 2.0932475884244375, "grad_norm": 23.325451994129086, "learning_rate": 2.5542397938435574e-06, "loss": 0.745391845703125, "step": 651 }, { "epoch": 2.0964630225080385, "grad_norm": 9.205824646857016, "learning_rate": 2.537927463538844e-06, "loss": 0.3058035969734192, "step": 652 }, { "epoch": 2.09967845659164, "grad_norm": 14.483317104386071, "learning_rate": 2.521649653661209e-06, "loss": 0.33844730257987976, "step": 653 }, { "epoch": 2.102893890675241, "grad_norm": 10.748115186443174, "learning_rate": 2.5054065924398934e-06, "loss": 0.3529083728790283, "step": 654 }, { "epoch": 2.1061093247588425, "grad_norm": 7.134237797900679, "learning_rate": 2.4891985076169356e-06, "loss": 0.3711613714694977, "step": 655 }, { "epoch": 2.1093247588424435, "grad_norm": 9.555120459648053, "learning_rate": 2.473025626443969e-06, "loss": 0.7479931712150574, "step": 656 }, { "epoch": 2.112540192926045, "grad_norm": 19.610879263288407, "learning_rate": 2.4568881756790436e-06, "loss": 1.7793715000152588, "step": 657 }, { "epoch": 2.1157556270096465, "grad_norm": 15.31483056892348, "learning_rate": 2.4407863815834414e-06, "loss": 1.3851677179336548, "step": 658 }, { "epoch": 2.1189710610932475, "grad_norm": 12.915717617411342, "learning_rate": 2.42472046991851e-06, "loss": 1.4731594324111938, "step": 659 }, { "epoch": 2.122186495176849, "grad_norm": 7.978020539846432, "learning_rate": 2.4086906659424904e-06, "loss": 0.5832240581512451, "step": 660 }, { "epoch": 2.12540192926045, "grad_norm": 8.57893982485209, "learning_rate": 2.392697194407363e-06, "loss": 0.18587762117385864, "step": 661 }, { "epoch": 2.1286173633440515, "grad_norm": 16.040640516050228, "learning_rate": 2.3767402795556953e-06, "loss": 1.4967979192733765, "step": 662 }, { "epoch": 2.1318327974276525, "grad_norm": 8.800901865323832, "learning_rate": 2.3608201451175004e-06, "loss": 0.6785554885864258, "step": 663 }, { "epoch": 2.135048231511254, "grad_norm": 8.369254419222456, "learning_rate": 2.3449370143070948e-06, "loss": 0.3392030596733093, "step": 664 }, { "epoch": 2.1382636655948555, "grad_norm": 13.581695588001903, "learning_rate": 2.329091109819972e-06, "loss": 1.3503499031066895, "step": 665 }, { "epoch": 2.1414790996784565, "grad_norm": 9.544273690674421, "learning_rate": 2.313282653829679e-06, "loss": 0.4895798861980438, "step": 666 }, { "epoch": 2.144694533762058, "grad_norm": 7.497690746653366, "learning_rate": 2.297511867984703e-06, "loss": 0.5282753109931946, "step": 667 }, { "epoch": 2.147909967845659, "grad_norm": 15.108645601163957, "learning_rate": 2.2817789734053626e-06, "loss": 0.44572100043296814, "step": 668 }, { "epoch": 2.1511254019292605, "grad_norm": 9.522046573188412, "learning_rate": 2.266084190680707e-06, "loss": 0.3825170397758484, "step": 669 }, { "epoch": 2.154340836012862, "grad_norm": 11.927142058431379, "learning_rate": 2.250427739865421e-06, "loss": 0.8217453360557556, "step": 670 }, { "epoch": 2.157556270096463, "grad_norm": 11.122450888975413, "learning_rate": 2.23480984047675e-06, "loss": 0.32945936918258667, "step": 671 }, { "epoch": 2.1607717041800645, "grad_norm": 10.060653422202963, "learning_rate": 2.219230711491406e-06, "loss": 0.3554953634738922, "step": 672 }, { "epoch": 2.1639871382636655, "grad_norm": 10.224259390532415, "learning_rate": 2.2036905713425104e-06, "loss": 0.7275658845901489, "step": 673 }, { "epoch": 2.167202572347267, "grad_norm": 9.307333936478546, "learning_rate": 2.1881896379165253e-06, "loss": 0.5208015441894531, "step": 674 }, { "epoch": 2.170418006430868, "grad_norm": 16.480106084286305, "learning_rate": 2.172728128550199e-06, "loss": 0.8410961627960205, "step": 675 }, { "epoch": 2.1736334405144695, "grad_norm": 23.43109332519012, "learning_rate": 2.1573062600275217e-06, "loss": 0.9196676015853882, "step": 676 }, { "epoch": 2.176848874598071, "grad_norm": 8.075311133528524, "learning_rate": 2.1419242485766834e-06, "loss": 0.4561595022678375, "step": 677 }, { "epoch": 2.180064308681672, "grad_norm": 6.991604551367555, "learning_rate": 2.126582309867041e-06, "loss": 0.2470824271440506, "step": 678 }, { "epoch": 2.1832797427652735, "grad_norm": 11.89113431006695, "learning_rate": 2.1112806590061006e-06, "loss": 0.366765558719635, "step": 679 }, { "epoch": 2.1864951768488745, "grad_norm": 7.200037824647487, "learning_rate": 2.0960195105364935e-06, "loss": 0.11232413351535797, "step": 680 }, { "epoch": 2.189710610932476, "grad_norm": 15.235602952570773, "learning_rate": 2.080799078432972e-06, "loss": 0.5797847509384155, "step": 681 }, { "epoch": 2.192926045016077, "grad_norm": 12.082768147438976, "learning_rate": 2.0656195760994104e-06, "loss": 0.3955646753311157, "step": 682 }, { "epoch": 2.1961414790996785, "grad_norm": 10.182906221123625, "learning_rate": 2.0504812163658104e-06, "loss": 0.27037519216537476, "step": 683 }, { "epoch": 2.19935691318328, "grad_norm": 16.725089320535528, "learning_rate": 2.0353842114853194e-06, "loss": 1.0738942623138428, "step": 684 }, { "epoch": 2.202572347266881, "grad_norm": 14.80956824571125, "learning_rate": 2.020328773131252e-06, "loss": 0.48105546832084656, "step": 685 }, { "epoch": 2.2057877813504825, "grad_norm": 14.488092854169647, "learning_rate": 2.005315112394122e-06, "loss": 0.37764203548431396, "step": 686 }, { "epoch": 2.2090032154340835, "grad_norm": 35.11784903119427, "learning_rate": 1.990343439778691e-06, "loss": 1.3033102750778198, "step": 687 }, { "epoch": 2.212218649517685, "grad_norm": 11.32083821956754, "learning_rate": 1.9754139652010025e-06, "loss": 0.3128071427345276, "step": 688 }, { "epoch": 2.215434083601286, "grad_norm": 7.739863787904974, "learning_rate": 1.9605268979854493e-06, "loss": 0.25044938921928406, "step": 689 }, { "epoch": 2.2186495176848875, "grad_norm": 9.336795568467322, "learning_rate": 1.9456824468618365e-06, "loss": 0.7681007981300354, "step": 690 }, { "epoch": 2.221864951768489, "grad_norm": 8.47441592443782, "learning_rate": 1.9308808199624518e-06, "loss": 0.8675619959831238, "step": 691 }, { "epoch": 2.22508038585209, "grad_norm": 13.531497358422932, "learning_rate": 1.9161222248191515e-06, "loss": 0.3523237109184265, "step": 692 }, { "epoch": 2.2282958199356915, "grad_norm": 7.7686044200353646, "learning_rate": 1.9014068683604475e-06, "loss": 0.5673654079437256, "step": 693 }, { "epoch": 2.2315112540192925, "grad_norm": 12.607843632159877, "learning_rate": 1.8867349569086064e-06, "loss": 0.4956747889518738, "step": 694 }, { "epoch": 2.234726688102894, "grad_norm": 20.83086061852303, "learning_rate": 1.8721066961767626e-06, "loss": 1.0982662439346313, "step": 695 }, { "epoch": 2.237942122186495, "grad_norm": 28.0587449883014, "learning_rate": 1.8575222912660224e-06, "loss": 0.7824825644493103, "step": 696 }, { "epoch": 2.2411575562700965, "grad_norm": 13.190430546984835, "learning_rate": 1.8429819466625993e-06, "loss": 0.9699738025665283, "step": 697 }, { "epoch": 2.244372990353698, "grad_norm": 9.095739529876795, "learning_rate": 1.8284858662349391e-06, "loss": 0.2911728620529175, "step": 698 }, { "epoch": 2.247588424437299, "grad_norm": 10.728396018637426, "learning_rate": 1.8140342532308675e-06, "loss": 0.21695515513420105, "step": 699 }, { "epoch": 2.2508038585209005, "grad_norm": 11.998687234131197, "learning_rate": 1.7996273102747363e-06, "loss": 0.5445791482925415, "step": 700 }, { "epoch": 2.2540192926045015, "grad_norm": 11.429548764717456, "learning_rate": 1.7852652393645842e-06, "loss": 0.5194580554962158, "step": 701 }, { "epoch": 2.257234726688103, "grad_norm": 7.56653505390186, "learning_rate": 1.7709482418693036e-06, "loss": 0.23896172642707825, "step": 702 }, { "epoch": 2.260450160771704, "grad_norm": 9.62095075841344, "learning_rate": 1.7566765185258205e-06, "loss": 0.35497206449508667, "step": 703 }, { "epoch": 2.2636655948553055, "grad_norm": 8.254578062437453, "learning_rate": 1.7424502694362755e-06, "loss": 0.5100143551826477, "step": 704 }, { "epoch": 2.266881028938907, "grad_norm": 9.058208468637773, "learning_rate": 1.7282696940652188e-06, "loss": 0.3519476652145386, "step": 705 }, { "epoch": 2.270096463022508, "grad_norm": 10.161898375908322, "learning_rate": 1.714134991236817e-06, "loss": 0.317427396774292, "step": 706 }, { "epoch": 2.2733118971061095, "grad_norm": 13.112579685570976, "learning_rate": 1.7000463591320621e-06, "loss": 0.2504899799823761, "step": 707 }, { "epoch": 2.2765273311897105, "grad_norm": 7.423757130841184, "learning_rate": 1.6860039952859941e-06, "loss": 0.6729331612586975, "step": 708 }, { "epoch": 2.279742765273312, "grad_norm": 10.935414242351301, "learning_rate": 1.672008096584931e-06, "loss": 0.2858375310897827, "step": 709 }, { "epoch": 2.282958199356913, "grad_norm": 7.614378612646665, "learning_rate": 1.658058859263708e-06, "loss": 0.2584810256958008, "step": 710 }, { "epoch": 2.2861736334405145, "grad_norm": 9.020570310988946, "learning_rate": 1.64415647890293e-06, "loss": 0.6542217135429382, "step": 711 }, { "epoch": 2.289389067524116, "grad_norm": 8.199722638862658, "learning_rate": 1.6303011504262223e-06, "loss": 0.7301985025405884, "step": 712 }, { "epoch": 2.292604501607717, "grad_norm": 16.272283444338548, "learning_rate": 1.6164930680975021e-06, "loss": 0.5628085136413574, "step": 713 }, { "epoch": 2.2958199356913185, "grad_norm": 10.028333472377934, "learning_rate": 1.6027324255182547e-06, "loss": 0.6142044067382812, "step": 714 }, { "epoch": 2.2990353697749195, "grad_norm": 8.45235295984565, "learning_rate": 1.5890194156248178e-06, "loss": 0.1730177402496338, "step": 715 }, { "epoch": 2.302250803858521, "grad_norm": 19.06820769510073, "learning_rate": 1.5753542306856774e-06, "loss": 0.44994986057281494, "step": 716 }, { "epoch": 2.305466237942122, "grad_norm": 13.015925232226362, "learning_rate": 1.5617370622987703e-06, "loss": 0.4153675436973572, "step": 717 }, { "epoch": 2.3086816720257235, "grad_norm": 15.815386750824745, "learning_rate": 1.548168101388799e-06, "loss": 0.7933076620101929, "step": 718 }, { "epoch": 2.311897106109325, "grad_norm": 6.8033416899165475, "learning_rate": 1.5346475382045578e-06, "loss": 0.2861023545265198, "step": 719 }, { "epoch": 2.315112540192926, "grad_norm": 7.586806061312669, "learning_rate": 1.5211755623162588e-06, "loss": 0.21383363008499146, "step": 720 }, { "epoch": 2.3183279742765275, "grad_norm": 8.35896871658916, "learning_rate": 1.507752362612878e-06, "loss": 0.34175100922584534, "step": 721 }, { "epoch": 2.3215434083601285, "grad_norm": 11.144091740266603, "learning_rate": 1.4943781272995073e-06, "loss": 0.6520302295684814, "step": 722 }, { "epoch": 2.32475884244373, "grad_norm": 9.891660748247679, "learning_rate": 1.481053043894713e-06, "loss": 0.47313952445983887, "step": 723 }, { "epoch": 2.327974276527331, "grad_norm": 10.01954348978427, "learning_rate": 1.467777299227911e-06, "loss": 0.43662163615226746, "step": 724 }, { "epoch": 2.3311897106109325, "grad_norm": 11.031433385009539, "learning_rate": 1.4545510794367413e-06, "loss": 0.8428820371627808, "step": 725 }, { "epoch": 2.334405144694534, "grad_norm": 8.663154574713626, "learning_rate": 1.4413745699644633e-06, "loss": 0.3453049063682556, "step": 726 }, { "epoch": 2.337620578778135, "grad_norm": 7.803079349836385, "learning_rate": 1.4282479555573559e-06, "loss": 0.2745356261730194, "step": 727 }, { "epoch": 2.3408360128617365, "grad_norm": 10.72034771606454, "learning_rate": 1.4151714202621214e-06, "loss": 0.5829728245735168, "step": 728 }, { "epoch": 2.3440514469453375, "grad_norm": 14.559259818421047, "learning_rate": 1.4021451474233111e-06, "loss": 0.599088191986084, "step": 729 }, { "epoch": 2.347266881028939, "grad_norm": 11.885109180133032, "learning_rate": 1.389169319680752e-06, "loss": 0.6071078777313232, "step": 730 }, { "epoch": 2.35048231511254, "grad_norm": 7.512662309336336, "learning_rate": 1.3762441189669855e-06, "loss": 0.7940813302993774, "step": 731 }, { "epoch": 2.3536977491961415, "grad_norm": 9.282805302910258, "learning_rate": 1.363369726504719e-06, "loss": 0.6212410926818848, "step": 732 }, { "epoch": 2.356913183279743, "grad_norm": 16.59514995951129, "learning_rate": 1.3505463228042814e-06, "loss": 0.7771339416503906, "step": 733 }, { "epoch": 2.360128617363344, "grad_norm": 8.019573283607059, "learning_rate": 1.337774087661095e-06, "loss": 0.3336787819862366, "step": 734 }, { "epoch": 2.3633440514469455, "grad_norm": 9.3480016042164, "learning_rate": 1.3250532001531568e-06, "loss": 0.3283434510231018, "step": 735 }, { "epoch": 2.3665594855305465, "grad_norm": 15.615069116375588, "learning_rate": 1.31238383863852e-06, "loss": 0.747290849685669, "step": 736 }, { "epoch": 2.369774919614148, "grad_norm": 11.478964562122078, "learning_rate": 1.2997661807528011e-06, "loss": 0.4145023226737976, "step": 737 }, { "epoch": 2.372990353697749, "grad_norm": 9.674102610648761, "learning_rate": 1.2872004034066843e-06, "loss": 0.6085692644119263, "step": 738 }, { "epoch": 2.3762057877813505, "grad_norm": 9.158481184369425, "learning_rate": 1.2746866827834443e-06, "loss": 0.35022085905075073, "step": 739 }, { "epoch": 2.379421221864952, "grad_norm": 10.878685805468756, "learning_rate": 1.2622251943364733e-06, "loss": 0.3418879210948944, "step": 740 }, { "epoch": 2.382636655948553, "grad_norm": 14.543864763023729, "learning_rate": 1.2498161127868236e-06, "loss": 0.48997265100479126, "step": 741 }, { "epoch": 2.3858520900321545, "grad_norm": 10.876583627678352, "learning_rate": 1.237459612120755e-06, "loss": 0.5536065697669983, "step": 742 }, { "epoch": 2.3890675241157555, "grad_norm": 20.351717332652505, "learning_rate": 1.2251558655873003e-06, "loss": 0.4042523205280304, "step": 743 }, { "epoch": 2.392282958199357, "grad_norm": 8.13192706557856, "learning_rate": 1.2129050456958296e-06, "loss": 0.3217351734638214, "step": 744 }, { "epoch": 2.395498392282958, "grad_norm": 7.539239428048716, "learning_rate": 1.2007073242136358e-06, "loss": 0.7380541563034058, "step": 745 }, { "epoch": 2.3987138263665595, "grad_norm": 10.893419775532118, "learning_rate": 1.1885628721635256e-06, "loss": 1.3607124090194702, "step": 746 }, { "epoch": 2.401929260450161, "grad_norm": 8.269742975582927, "learning_rate": 1.176471859821421e-06, "loss": 0.5945987701416016, "step": 747 }, { "epoch": 2.405144694533762, "grad_norm": 10.313373636714106, "learning_rate": 1.1644344567139716e-06, "loss": 0.44915276765823364, "step": 748 }, { "epoch": 2.4083601286173635, "grad_norm": 9.146019028304934, "learning_rate": 1.1524508316161799e-06, "loss": 0.38859468698501587, "step": 749 }, { "epoch": 2.4115755627009645, "grad_norm": 13.294635461287648, "learning_rate": 1.1405211525490307e-06, "loss": 0.20568466186523438, "step": 750 }, { "epoch": 2.414790996784566, "grad_norm": 11.70213362190279, "learning_rate": 1.1286455867771422e-06, "loss": 0.6367174983024597, "step": 751 }, { "epoch": 2.418006430868167, "grad_norm": 10.461363981706414, "learning_rate": 1.1168243008064123e-06, "loss": 0.30549776554107666, "step": 752 }, { "epoch": 2.4212218649517685, "grad_norm": 10.69031162106857, "learning_rate": 1.1050574603816905e-06, "loss": 0.37557756900787354, "step": 753 }, { "epoch": 2.42443729903537, "grad_norm": 7.379872280064574, "learning_rate": 1.0933452304844505e-06, "loss": 0.5297196507453918, "step": 754 }, { "epoch": 2.427652733118971, "grad_norm": 9.7634723677066, "learning_rate": 1.0816877753304777e-06, "loss": 0.274686723947525, "step": 755 }, { "epoch": 2.4308681672025725, "grad_norm": 7.237746575511637, "learning_rate": 1.0700852583675708e-06, "loss": 0.33781081438064575, "step": 756 }, { "epoch": 2.4340836012861735, "grad_norm": 10.197522367598072, "learning_rate": 1.0585378422732435e-06, "loss": 0.3239028751850128, "step": 757 }, { "epoch": 2.437299035369775, "grad_norm": 9.392166371827608, "learning_rate": 1.0470456889524473e-06, "loss": 0.34594273567199707, "step": 758 }, { "epoch": 2.440514469453376, "grad_norm": 6.796254455681624, "learning_rate": 1.0356089595353008e-06, "loss": 0.21343210339546204, "step": 759 }, { "epoch": 2.4437299035369775, "grad_norm": 7.480509218493879, "learning_rate": 1.0242278143748307e-06, "loss": 0.49799197912216187, "step": 760 }, { "epoch": 2.446945337620579, "grad_norm": 8.95241961534226, "learning_rate": 1.012902413044725e-06, "loss": 0.3868298828601837, "step": 761 }, { "epoch": 2.45016077170418, "grad_norm": 10.42651529337544, "learning_rate": 1.0016329143370929e-06, "loss": 0.264824241399765, "step": 762 }, { "epoch": 2.4533762057877815, "grad_norm": 9.17833598375061, "learning_rate": 9.904194762602382e-07, "loss": 0.3985700011253357, "step": 763 }, { "epoch": 2.4565916398713825, "grad_norm": 9.674121185768858, "learning_rate": 9.792622560364467e-07, "loss": 0.17972898483276367, "step": 764 }, { "epoch": 2.459807073954984, "grad_norm": 8.206523942923813, "learning_rate": 9.681614100997806e-07, "loss": 0.3820546865463257, "step": 765 }, { "epoch": 2.463022508038585, "grad_norm": 8.778341452335091, "learning_rate": 9.57117094093884e-07, "loss": 0.13588829338550568, "step": 766 }, { "epoch": 2.4662379421221865, "grad_norm": 12.703644433268686, "learning_rate": 9.46129462869802e-07, "loss": 0.2940727472305298, "step": 767 }, { "epoch": 2.469453376205788, "grad_norm": 10.30882189666681, "learning_rate": 9.351986704838084e-07, "loss": 0.6208051443099976, "step": 768 }, { "epoch": 2.472668810289389, "grad_norm": 9.88354985018698, "learning_rate": 9.243248701952489e-07, "loss": 0.9009281396865845, "step": 769 }, { "epoch": 2.4758842443729905, "grad_norm": 7.057277121900955, "learning_rate": 9.135082144643869e-07, "loss": 0.3825221061706543, "step": 770 }, { "epoch": 2.4790996784565915, "grad_norm": 13.283010516967643, "learning_rate": 9.0274885495027e-07, "loss": 0.4601898789405823, "step": 771 }, { "epoch": 2.482315112540193, "grad_norm": 9.034062537915768, "learning_rate": 8.92046942508602e-07, "loss": 0.31752362847328186, "step": 772 }, { "epoch": 2.485530546623794, "grad_norm": 9.886229624024415, "learning_rate": 8.814026271896275e-07, "loss": 0.9294736981391907, "step": 773 }, { "epoch": 2.4887459807073955, "grad_norm": 13.589832734358895, "learning_rate": 8.708160582360303e-07, "loss": 0.324219286441803, "step": 774 }, { "epoch": 2.491961414790997, "grad_norm": 11.552870172052325, "learning_rate": 8.602873840808379e-07, "loss": 0.9777847528457642, "step": 775 }, { "epoch": 2.495176848874598, "grad_norm": 14.788050425785567, "learning_rate": 8.498167523453404e-07, "loss": 0.5360197424888611, "step": 776 }, { "epoch": 2.4983922829581995, "grad_norm": 13.424208182029288, "learning_rate": 8.394043098370275e-07, "loss": 0.31830108165740967, "step": 777 }, { "epoch": 2.5016077170418005, "grad_norm": 20.795163896337453, "learning_rate": 8.290502025475183e-07, "loss": 0.9196930527687073, "step": 778 }, { "epoch": 2.504823151125402, "grad_norm": 13.342352710693937, "learning_rate": 8.187545756505244e-07, "loss": 0.5551115870475769, "step": 779 }, { "epoch": 2.508038585209003, "grad_norm": 10.381356116441133, "learning_rate": 8.085175734998091e-07, "loss": 0.6043642163276672, "step": 780 }, { "epoch": 2.5112540192926045, "grad_norm": 6.062655557368801, "learning_rate": 7.98339339627166e-07, "loss": 0.22657924890518188, "step": 781 }, { "epoch": 2.514469453376206, "grad_norm": 10.807014185724375, "learning_rate": 7.882200167404047e-07, "loss": 0.259809672832489, "step": 782 }, { "epoch": 2.517684887459807, "grad_norm": 7.872967554652684, "learning_rate": 7.781597467213514e-07, "loss": 0.4243828058242798, "step": 783 }, { "epoch": 2.5209003215434085, "grad_norm": 14.382598474640337, "learning_rate": 7.681586706238586e-07, "loss": 0.5216907858848572, "step": 784 }, { "epoch": 2.5241157556270095, "grad_norm": 6.741881997512629, "learning_rate": 7.582169286718305e-07, "loss": 0.260081946849823, "step": 785 }, { "epoch": 2.527331189710611, "grad_norm": 7.491622137828397, "learning_rate": 7.483346602572505e-07, "loss": 0.3229532837867737, "step": 786 }, { "epoch": 2.530546623794212, "grad_norm": 12.51190036363299, "learning_rate": 7.385120039382326e-07, "loss": 1.6990151405334473, "step": 787 }, { "epoch": 2.5337620578778135, "grad_norm": 12.102101725870327, "learning_rate": 7.287490974370759e-07, "loss": 0.46230068802833557, "step": 788 }, { "epoch": 2.536977491961415, "grad_norm": 7.3789531863557, "learning_rate": 7.190460776383351e-07, "loss": 0.1410602331161499, "step": 789 }, { "epoch": 2.540192926045016, "grad_norm": 8.791343590023278, "learning_rate": 7.094030805869001e-07, "loss": 0.1462668925523758, "step": 790 }, { "epoch": 2.5434083601286175, "grad_norm": 11.499145842643497, "learning_rate": 6.998202414860894e-07, "loss": 0.4931030869483948, "step": 791 }, { "epoch": 2.5466237942122185, "grad_norm": 8.890241677567976, "learning_rate": 6.902976946957518e-07, "loss": 0.4790411591529846, "step": 792 }, { "epoch": 2.54983922829582, "grad_norm": 7.357169662653574, "learning_rate": 6.808355737303895e-07, "loss": 0.25933071970939636, "step": 793 }, { "epoch": 2.553054662379421, "grad_norm": 18.008951919388966, "learning_rate": 6.71434011257277e-07, "loss": 0.7769885063171387, "step": 794 }, { "epoch": 2.5562700964630225, "grad_norm": 15.216768610586033, "learning_rate": 6.620931390946078e-07, "loss": 0.9100818634033203, "step": 795 }, { "epoch": 2.559485530546624, "grad_norm": 10.749117948962583, "learning_rate": 6.528130882096418e-07, "loss": 0.31192898750305176, "step": 796 }, { "epoch": 2.562700964630225, "grad_norm": 11.371166952776898, "learning_rate": 6.435939887168718e-07, "loss": 0.29440587759017944, "step": 797 }, { "epoch": 2.5659163987138265, "grad_norm": 9.195291843958517, "learning_rate": 6.344359698761998e-07, "loss": 0.3736717402935028, "step": 798 }, { "epoch": 2.5691318327974275, "grad_norm": 13.644043776235835, "learning_rate": 6.253391600911213e-07, "loss": 0.6370671391487122, "step": 799 }, { "epoch": 2.572347266881029, "grad_norm": 17.84760553493272, "learning_rate": 6.163036869069267e-07, "loss": 1.8662174940109253, "step": 800 }, { "epoch": 2.57556270096463, "grad_norm": 8.898342133449939, "learning_rate": 6.073296770089159e-07, "loss": 0.4110758900642395, "step": 801 }, { "epoch": 2.5787781350482315, "grad_norm": 13.204596578832312, "learning_rate": 5.984172562206164e-07, "loss": 0.26106947660446167, "step": 802 }, { "epoch": 2.581993569131833, "grad_norm": 10.376179325495649, "learning_rate": 5.895665495020242e-07, "loss": 0.25730016827583313, "step": 803 }, { "epoch": 2.585209003215434, "grad_norm": 13.684680313080825, "learning_rate": 5.807776809478472e-07, "loss": 0.3436719477176666, "step": 804 }, { "epoch": 2.5884244372990355, "grad_norm": 27.176558442062554, "learning_rate": 5.720507737857706e-07, "loss": 1.1672216653823853, "step": 805 }, { "epoch": 2.5916398713826365, "grad_norm": 12.887853458109294, "learning_rate": 5.633859503747241e-07, "loss": 0.5256634950637817, "step": 806 }, { "epoch": 2.594855305466238, "grad_norm": 8.96694135103656, "learning_rate": 5.547833322031693e-07, "loss": 0.366617888212204, "step": 807 }, { "epoch": 2.598070739549839, "grad_norm": 9.412357022980187, "learning_rate": 5.462430398873947e-07, "loss": 0.27508530020713806, "step": 808 }, { "epoch": 2.6012861736334405, "grad_norm": 9.133709325093466, "learning_rate": 5.377651931698275e-07, "loss": 0.36251911520957947, "step": 809 }, { "epoch": 2.604501607717042, "grad_norm": 9.848470581534286, "learning_rate": 5.293499109173517e-07, "loss": 0.33935314416885376, "step": 810 }, { "epoch": 2.607717041800643, "grad_norm": 14.662987456896733, "learning_rate": 5.209973111196404e-07, "loss": 0.4906863570213318, "step": 811 }, { "epoch": 2.6109324758842445, "grad_norm": 26.400737908261828, "learning_rate": 5.127075108875051e-07, "loss": 1.5506454706192017, "step": 812 }, { "epoch": 2.6141479099678455, "grad_norm": 12.023484760258915, "learning_rate": 5.044806264512525e-07, "loss": 0.2666461765766144, "step": 813 }, { "epoch": 2.617363344051447, "grad_norm": 12.371598029084595, "learning_rate": 4.963167731590535e-07, "loss": 0.6199164986610413, "step": 814 }, { "epoch": 2.620578778135048, "grad_norm": 9.073073795027149, "learning_rate": 4.88216065475327e-07, "loss": 0.2723952531814575, "step": 815 }, { "epoch": 2.6237942122186495, "grad_norm": 8.758785690157431, "learning_rate": 4.801786169791339e-07, "loss": 0.46878230571746826, "step": 816 }, { "epoch": 2.627009646302251, "grad_norm": 9.483949934382007, "learning_rate": 4.7220454036258803e-07, "loss": 0.36121273040771484, "step": 817 }, { "epoch": 2.630225080385852, "grad_norm": 9.850946982616728, "learning_rate": 4.642939474292713e-07, "loss": 0.38482001423835754, "step": 818 }, { "epoch": 2.6334405144694535, "grad_norm": 14.43891373480777, "learning_rate": 4.5644694909266984e-07, "loss": 0.6713676452636719, "step": 819 }, { "epoch": 2.6366559485530545, "grad_norm": 10.446474380940323, "learning_rate": 4.4866365537461543e-07, "loss": 0.4145408868789673, "step": 820 }, { "epoch": 2.639871382636656, "grad_norm": 7.984266402601969, "learning_rate": 4.4094417540374745e-07, "loss": 0.18469397723674774, "step": 821 }, { "epoch": 2.643086816720257, "grad_norm": 12.587060023396914, "learning_rate": 4.332886174139794e-07, "loss": 0.9125012159347534, "step": 822 }, { "epoch": 2.6463022508038585, "grad_norm": 7.989834221712064, "learning_rate": 4.2569708874298123e-07, "loss": 0.7010893225669861, "step": 823 }, { "epoch": 2.64951768488746, "grad_norm": 10.71200284540403, "learning_rate": 4.1816969583067526e-07, "loss": 0.22042930126190186, "step": 824 }, { "epoch": 2.652733118971061, "grad_norm": 8.632776088215412, "learning_rate": 4.1070654421774767e-07, "loss": 0.8344212770462036, "step": 825 }, { "epoch": 2.6559485530546625, "grad_norm": 16.33719255777251, "learning_rate": 4.0330773854416025e-07, "loss": 0.3559122681617737, "step": 826 }, { "epoch": 2.6591639871382635, "grad_norm": 11.020551860792871, "learning_rate": 3.959733825476908e-07, "loss": 0.30302202701568604, "step": 827 }, { "epoch": 2.662379421221865, "grad_norm": 11.593833422236477, "learning_rate": 3.8870357906247434e-07, "loss": 0.37081068754196167, "step": 828 }, { "epoch": 2.665594855305466, "grad_norm": 10.818672631896604, "learning_rate": 3.814984300175645e-07, "loss": 0.2318996787071228, "step": 829 }, { "epoch": 2.6688102893890675, "grad_norm": 10.490748477323145, "learning_rate": 3.743580364355004e-07, "loss": 0.27689433097839355, "step": 830 }, { "epoch": 2.672025723472669, "grad_norm": 7.557342296482055, "learning_rate": 3.672824984308948e-07, "loss": 0.3493078351020813, "step": 831 }, { "epoch": 2.67524115755627, "grad_norm": 19.55126309686112, "learning_rate": 3.602719152090256e-07, "loss": 0.7462046146392822, "step": 832 }, { "epoch": 2.6784565916398715, "grad_norm": 9.221894655944931, "learning_rate": 3.533263850644508e-07, "loss": 0.6614691615104675, "step": 833 }, { "epoch": 2.6816720257234725, "grad_norm": 9.211741634507469, "learning_rate": 3.464460053796237e-07, "loss": 0.29138296842575073, "step": 834 }, { "epoch": 2.684887459807074, "grad_norm": 9.734125500615347, "learning_rate": 3.396308726235326e-07, "loss": 0.5526795387268066, "step": 835 }, { "epoch": 2.688102893890675, "grad_norm": 10.836649082695137, "learning_rate": 3.328810823503448e-07, "loss": 0.5932884812355042, "step": 836 }, { "epoch": 2.6913183279742765, "grad_norm": 10.19243735016382, "learning_rate": 3.2619672919807054e-07, "loss": 0.6854689121246338, "step": 837 }, { "epoch": 2.694533762057878, "grad_norm": 14.297447936460108, "learning_rate": 3.195779068872318e-07, "loss": 0.2756684422492981, "step": 838 }, { "epoch": 2.697749196141479, "grad_norm": 10.266269542405677, "learning_rate": 3.1302470821955143e-07, "loss": 0.30567488074302673, "step": 839 }, { "epoch": 2.7009646302250805, "grad_norm": 10.298881489172567, "learning_rate": 3.0653722507665016e-07, "loss": 0.8650332093238831, "step": 840 }, { "epoch": 2.7041800643086815, "grad_norm": 12.33005217016299, "learning_rate": 3.0011554841876236e-07, "loss": 0.7738863229751587, "step": 841 }, { "epoch": 2.707395498392283, "grad_norm": 13.788201933128668, "learning_rate": 2.9375976828345254e-07, "loss": 0.4506850838661194, "step": 842 }, { "epoch": 2.710610932475884, "grad_norm": 23.437927191055728, "learning_rate": 2.8746997378436117e-07, "loss": 0.9781379699707031, "step": 843 }, { "epoch": 2.7138263665594855, "grad_norm": 8.156853967408997, "learning_rate": 2.8124625310995136e-07, "loss": 0.36554017663002014, "step": 844 }, { "epoch": 2.717041800643087, "grad_norm": 36.113062108363714, "learning_rate": 2.750886935222724e-07, "loss": 1.2861707210540771, "step": 845 }, { "epoch": 2.720257234726688, "grad_norm": 9.707027837669324, "learning_rate": 2.689973813557367e-07, "loss": 0.30182671546936035, "step": 846 }, { "epoch": 2.7234726688102895, "grad_norm": 8.613290992443563, "learning_rate": 2.6297240201591025e-07, "loss": 0.3068884015083313, "step": 847 }, { "epoch": 2.7266881028938905, "grad_norm": 10.585291997817569, "learning_rate": 2.5701383997831284e-07, "loss": 0.3039591610431671, "step": 848 }, { "epoch": 2.729903536977492, "grad_norm": 16.036360689461798, "learning_rate": 2.5112177878723833e-07, "loss": 0.4938279986381531, "step": 849 }, { "epoch": 2.733118971061093, "grad_norm": 7.7246780557178045, "learning_rate": 2.452963010545767e-07, "loss": 0.3451383709907532, "step": 850 }, { "epoch": 2.7363344051446945, "grad_norm": 11.562492840025135, "learning_rate": 2.3953748845866096e-07, "loss": 0.29905378818511963, "step": 851 }, { "epoch": 2.739549839228296, "grad_norm": 13.062794280899158, "learning_rate": 2.3384542174311908e-07, "loss": 0.3758173882961273, "step": 852 }, { "epoch": 2.742765273311897, "grad_norm": 10.466966734307, "learning_rate": 2.282201807157436e-07, "loss": 0.7077566981315613, "step": 853 }, { "epoch": 2.7459807073954985, "grad_norm": 23.68854074954466, "learning_rate": 2.2266184424737214e-07, "loss": 0.5676212310791016, "step": 854 }, { "epoch": 2.7491961414790995, "grad_norm": 10.931312601197227, "learning_rate": 2.1717049027078106e-07, "loss": 0.3098456859588623, "step": 855 }, { "epoch": 2.752411575562701, "grad_norm": 13.915496014810294, "learning_rate": 2.1174619577959355e-07, "loss": 0.5395633578300476, "step": 856 }, { "epoch": 2.755627009646302, "grad_norm": 11.883754001722993, "learning_rate": 2.0638903682719814e-07, "loss": 0.67840975522995, "step": 857 }, { "epoch": 2.7588424437299035, "grad_norm": 9.072301219104835, "learning_rate": 2.010990885256875e-07, "loss": 0.22875866293907166, "step": 858 }, { "epoch": 2.762057877813505, "grad_norm": 11.388523965575855, "learning_rate": 1.958764250447981e-07, "loss": 0.28753116726875305, "step": 859 }, { "epoch": 2.765273311897106, "grad_norm": 10.42746808832713, "learning_rate": 1.9072111961087546e-07, "loss": 0.49607959389686584, "step": 860 }, { "epoch": 2.7684887459807075, "grad_norm": 8.55806623128332, "learning_rate": 1.856332445058462e-07, "loss": 0.503407895565033, "step": 861 }, { "epoch": 2.7717041800643085, "grad_norm": 12.297262248101239, "learning_rate": 1.8061287106620308e-07, "loss": 0.37309232354164124, "step": 862 }, { "epoch": 2.77491961414791, "grad_norm": 6.834698795090784, "learning_rate": 1.7566006968200712e-07, "loss": 0.15657085180282593, "step": 863 }, { "epoch": 2.778135048231511, "grad_norm": 11.42404497830935, "learning_rate": 1.7077490979589996e-07, "loss": 0.9316859245300293, "step": 864 }, { "epoch": 2.7813504823151125, "grad_norm": 24.35923106389002, "learning_rate": 1.6595745990212686e-07, "loss": 0.5050212144851685, "step": 865 }, { "epoch": 2.784565916398714, "grad_norm": 8.48025747992941, "learning_rate": 1.6120778754558418e-07, "loss": 0.2638796865940094, "step": 866 }, { "epoch": 2.787781350482315, "grad_norm": 10.634566725803458, "learning_rate": 1.5652595932086346e-07, "loss": 0.3945295214653015, "step": 867 }, { "epoch": 2.7909967845659165, "grad_norm": 10.867738538207686, "learning_rate": 1.519120408713237e-07, "loss": 0.7213743925094604, "step": 868 }, { "epoch": 2.7942122186495175, "grad_norm": 14.418328198181541, "learning_rate": 1.4736609688816738e-07, "loss": 0.3248399794101715, "step": 869 }, { "epoch": 2.797427652733119, "grad_norm": 8.419980675343098, "learning_rate": 1.42888191109537e-07, "loss": 0.22939413785934448, "step": 870 }, { "epoch": 2.80064308681672, "grad_norm": 9.19433579405382, "learning_rate": 1.3847838631961764e-07, "loss": 0.32842016220092773, "step": 871 }, { "epoch": 2.8038585209003215, "grad_norm": 10.639689045879424, "learning_rate": 1.341367443477598e-07, "loss": 0.35260647535324097, "step": 872 }, { "epoch": 2.807073954983923, "grad_norm": 7.268481225335977, "learning_rate": 1.2986332606761077e-07, "loss": 0.14097937941551208, "step": 873 }, { "epoch": 2.810289389067524, "grad_norm": 12.654855752821373, "learning_rate": 1.2565819139626123e-07, "loss": 0.3869823217391968, "step": 874 }, { "epoch": 2.8135048231511255, "grad_norm": 12.375199769540473, "learning_rate": 1.215213992934061e-07, "loss": 0.37241262197494507, "step": 875 }, { "epoch": 2.816720257234727, "grad_norm": 11.840995986503778, "learning_rate": 1.1745300776051683e-07, "loss": 0.4987008273601532, "step": 876 }, { "epoch": 2.819935691318328, "grad_norm": 20.150747698775717, "learning_rate": 1.1345307384002857e-07, "loss": 0.7997194528579712, "step": 877 }, { "epoch": 2.823151125401929, "grad_norm": 11.222276595989268, "learning_rate": 1.0952165361454103e-07, "loss": 0.3447033166885376, "step": 878 }, { "epoch": 2.8263665594855305, "grad_norm": 10.642677007946524, "learning_rate": 1.0565880220603009e-07, "loss": 0.3858156204223633, "step": 879 }, { "epoch": 2.829581993569132, "grad_norm": 9.185432192229552, "learning_rate": 1.0186457377507786e-07, "loss": 0.34079843759536743, "step": 880 }, { "epoch": 2.832797427652733, "grad_norm": 11.088590201340256, "learning_rate": 9.813902152011112e-08, "loss": 0.23632663488388062, "step": 881 }, { "epoch": 2.8360128617363345, "grad_norm": 8.103072227415286, "learning_rate": 9.448219767665579e-08, "loss": 0.27433305978775024, "step": 882 }, { "epoch": 2.839228295819936, "grad_norm": 12.74986410220812, "learning_rate": 9.089415351660635e-08, "loss": 0.23926009237766266, "step": 883 }, { "epoch": 2.842443729903537, "grad_norm": 9.837558952269603, "learning_rate": 8.737493934750374e-08, "loss": 0.2923390567302704, "step": 884 }, { "epoch": 2.845659163987138, "grad_norm": 8.70335385161108, "learning_rate": 8.392460451183304e-08, "loss": 0.41260838508605957, "step": 885 }, { "epoch": 2.8488745980707395, "grad_norm": 14.688290879664716, "learning_rate": 8.05431973863291e-08, "loss": 1.014516830444336, "step": 886 }, { "epoch": 2.852090032154341, "grad_norm": 9.853101244202293, "learning_rate": 7.723076538130093e-08, "loss": 0.7642203569412231, "step": 887 }, { "epoch": 2.855305466237942, "grad_norm": 21.13860057153763, "learning_rate": 7.398735493996445e-08, "loss": 0.5412633419036865, "step": 888 }, { "epoch": 2.8585209003215435, "grad_norm": 6.858041915122581, "learning_rate": 7.081301153779308e-08, "loss": 0.2149556279182434, "step": 889 }, { "epoch": 2.861736334405145, "grad_norm": 8.692720770718445, "learning_rate": 6.77077796818787e-08, "loss": 0.2750585675239563, "step": 890 }, { "epoch": 2.864951768488746, "grad_norm": 11.520297885410352, "learning_rate": 6.467170291030999e-08, "loss": 0.870136022567749, "step": 891 }, { "epoch": 2.868167202572347, "grad_norm": 7.431835115778323, "learning_rate": 6.170482379155907e-08, "loss": 0.6092904806137085, "step": 892 }, { "epoch": 2.8713826366559485, "grad_norm": 6.6845295035921035, "learning_rate": 5.880718392388518e-08, "loss": 0.3216220438480377, "step": 893 }, { "epoch": 2.87459807073955, "grad_norm": 12.92591336560967, "learning_rate": 5.597882393475473e-08, "loss": 0.9828184247016907, "step": 894 }, { "epoch": 2.877813504823151, "grad_norm": 12.3805351827977, "learning_rate": 5.3219783480266685e-08, "loss": 0.3474922776222229, "step": 895 }, { "epoch": 2.8810289389067525, "grad_norm": 8.250380956070305, "learning_rate": 5.053010124460078e-08, "loss": 0.6136802434921265, "step": 896 }, { "epoch": 2.884244372990354, "grad_norm": 10.183182722886206, "learning_rate": 4.790981493947244e-08, "loss": 0.36145269870758057, "step": 897 }, { "epoch": 2.887459807073955, "grad_norm": 10.874247692186005, "learning_rate": 4.5358961303604845e-08, "loss": 0.582977831363678, "step": 898 }, { "epoch": 2.890675241157556, "grad_norm": 7.351347894780587, "learning_rate": 4.287757610221488e-08, "loss": 0.26535022258758545, "step": 899 }, { "epoch": 2.8938906752411575, "grad_norm": 8.630676257377292, "learning_rate": 4.046569412651025e-08, "loss": 0.36218592524528503, "step": 900 }, { "epoch": 2.897106109324759, "grad_norm": 16.143200059875355, "learning_rate": 3.8123349193201484e-08, "loss": 0.6273083686828613, "step": 901 }, { "epoch": 2.90032154340836, "grad_norm": 13.043811958366279, "learning_rate": 3.585057414402959e-08, "loss": 0.51048743724823, "step": 902 }, { "epoch": 2.9035369774919615, "grad_norm": 13.302923874937125, "learning_rate": 3.364740084530416e-08, "loss": 0.3014843165874481, "step": 903 }, { "epoch": 2.906752411575563, "grad_norm": 14.89983151718059, "learning_rate": 3.1513860187457055e-08, "loss": 0.2004130780696869, "step": 904 }, { "epoch": 2.909967845659164, "grad_norm": 9.790667693555704, "learning_rate": 2.9449982084607808e-08, "loss": 0.39281973242759705, "step": 905 }, { "epoch": 2.913183279742765, "grad_norm": 18.644324884396916, "learning_rate": 2.7455795474147228e-08, "loss": 0.23955759406089783, "step": 906 }, { "epoch": 2.9163987138263665, "grad_norm": 8.927013412093052, "learning_rate": 2.5531328316328875e-08, "loss": 0.20128212869167328, "step": 907 }, { "epoch": 2.919614147909968, "grad_norm": 15.799239685702284, "learning_rate": 2.367660759387935e-08, "loss": 0.7717773914337158, "step": 908 }, { "epoch": 2.922829581993569, "grad_norm": 15.772125165413822, "learning_rate": 2.189165931161752e-08, "loss": 0.36580389738082886, "step": 909 }, { "epoch": 2.9260450160771705, "grad_norm": 9.375529241824653, "learning_rate": 2.017650849609143e-08, "loss": 0.20489028096199036, "step": 910 }, { "epoch": 2.929260450160772, "grad_norm": 9.02286597270734, "learning_rate": 1.8531179195227512e-08, "loss": 0.4565661549568176, "step": 911 }, { "epoch": 2.932475884244373, "grad_norm": 8.336347819565956, "learning_rate": 1.6955694477993055e-08, "loss": 0.1987374871969223, "step": 912 }, { "epoch": 2.935691318327974, "grad_norm": 11.104808526073217, "learning_rate": 1.545007643407148e-08, "loss": 0.6139571070671082, "step": 913 }, { "epoch": 2.9389067524115755, "grad_norm": 19.520039784387993, "learning_rate": 1.4014346173555904e-08, "loss": 0.3137204647064209, "step": 914 }, { "epoch": 2.942122186495177, "grad_norm": 11.947768453886892, "learning_rate": 1.2648523826649384e-08, "loss": 0.2887860834598541, "step": 915 }, { "epoch": 2.945337620578778, "grad_norm": 12.055012811370135, "learning_rate": 1.1352628543385702e-08, "loss": 0.20143553614616394, "step": 916 }, { "epoch": 2.9485530546623795, "grad_norm": 9.518048446591854, "learning_rate": 1.0126678493358466e-08, "loss": 0.4039468765258789, "step": 917 }, { "epoch": 2.951768488745981, "grad_norm": 6.847191516049079, "learning_rate": 8.97069086546798e-09, "loss": 0.22868111729621887, "step": 918 }, { "epoch": 2.954983922829582, "grad_norm": 8.642631440592353, "learning_rate": 7.884681867679766e-09, "loss": 0.7044589519500732, "step": 919 }, { "epoch": 2.958199356913183, "grad_norm": 7.259843508692505, "learning_rate": 6.86866672679698e-09, "loss": 0.17346805334091187, "step": 920 }, { "epoch": 2.9614147909967845, "grad_norm": 8.999484586415532, "learning_rate": 5.9226596882483445e-09, "loss": 0.6509414911270142, "step": 921 }, { "epoch": 2.964630225080386, "grad_norm": 9.496798526213007, "learning_rate": 5.0466740158849895e-09, "loss": 0.25824788212776184, "step": 922 }, { "epoch": 2.967845659163987, "grad_norm": 8.918273839634464, "learning_rate": 4.240721991799479e-09, "loss": 0.40939438343048096, "step": 923 }, { "epoch": 2.9710610932475885, "grad_norm": 7.676643145381744, "learning_rate": 3.5048149161487356e-09, "loss": 0.2906154692173004, "step": 924 }, { "epoch": 2.97427652733119, "grad_norm": 9.78535730660284, "learning_rate": 2.8389631069986044e-09, "loss": 0.7982381582260132, "step": 925 }, { "epoch": 2.977491961414791, "grad_norm": 8.125146432986423, "learning_rate": 2.2431759001789734e-09, "loss": 0.39818036556243896, "step": 926 }, { "epoch": 2.980707395498392, "grad_norm": 8.127002382258551, "learning_rate": 1.7174616491510975e-09, "loss": 0.311463862657547, "step": 927 }, { "epoch": 2.9839228295819935, "grad_norm": 9.126971708317253, "learning_rate": 1.2618277248921397e-09, "loss": 0.8928610682487488, "step": 928 }, { "epoch": 2.987138263665595, "grad_norm": 13.640832208032544, "learning_rate": 8.762805157913612e-10, "loss": 0.5860022306442261, "step": 929 }, { "epoch": 2.990353697749196, "grad_norm": 11.44603238864219, "learning_rate": 5.608254275607516e-10, "loss": 0.244879812002182, "step": 930 }, { "epoch": 2.9935691318327975, "grad_norm": 11.900949930490297, "learning_rate": 3.1546688315842177e-10, "loss": 0.37080761790275574, "step": 931 }, { "epoch": 2.996784565916399, "grad_norm": 11.46303644524341, "learning_rate": 1.4020832272754193e-10, "loss": 0.3129621148109436, "step": 932 }, { "epoch": 3.0, "grad_norm": 7.767345085481768, "learning_rate": 3.505220354749206e-11, "loss": 0.548541247844696, "step": 933 }, { "epoch": 3.0, "step": 933, "total_flos": 2578979020800.0, "train_loss": 1.6905082198137384, "train_runtime": 1266.0882, "train_samples_per_second": 2.945, "train_steps_per_second": 0.737 } ], "logging_steps": 1, "max_steps": 933, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 2578979020800.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }