{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.6350174216027874, "eval_steps": 500, "global_step": 1458, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00043554006968641115, "grad_norm": 20.063322067260742, "learning_rate": 0.0, "loss": 0.5311915874481201, "step": 1 }, { "epoch": 0.0008710801393728223, "grad_norm": 16.711223602294922, "learning_rate": 7.894736842105263e-07, "loss": 0.4841555058956146, "step": 2 }, { "epoch": 0.0013066202090592336, "grad_norm": 20.928285598754883, "learning_rate": 1.5789473684210526e-06, "loss": 0.5376076698303223, "step": 3 }, { "epoch": 0.0017421602787456446, "grad_norm": 12.274636268615723, "learning_rate": 2.368421052631579e-06, "loss": 0.4652983248233795, "step": 4 }, { "epoch": 0.0021777003484320556, "grad_norm": 9.006216049194336, "learning_rate": 3.157894736842105e-06, "loss": 0.4457506537437439, "step": 5 }, { "epoch": 0.002613240418118467, "grad_norm": 9.691102981567383, "learning_rate": 3.9473684210526315e-06, "loss": 0.4195502698421478, "step": 6 }, { "epoch": 0.003048780487804878, "grad_norm": 7.529472827911377, "learning_rate": 4.736842105263158e-06, "loss": 0.38654863834381104, "step": 7 }, { "epoch": 0.003484320557491289, "grad_norm": 7.6599836349487305, "learning_rate": 5.526315789473684e-06, "loss": 0.34040379524230957, "step": 8 }, { "epoch": 0.0039198606271777, "grad_norm": 10.03175163269043, "learning_rate": 6.31578947368421e-06, "loss": 0.4091436266899109, "step": 9 }, { "epoch": 0.004355400696864111, "grad_norm": 6.276109218597412, "learning_rate": 7.105263157894737e-06, "loss": 0.28801435232162476, "step": 10 }, { "epoch": 0.004790940766550522, "grad_norm": 7.701242923736572, "learning_rate": 7.894736842105263e-06, "loss": 0.2946423590183258, "step": 11 }, { "epoch": 0.005226480836236934, "grad_norm": 11.896566390991211, "learning_rate": 8.68421052631579e-06, "loss": 0.27176377177238464, "step": 12 }, { "epoch": 0.005662020905923345, "grad_norm": 7.672152519226074, "learning_rate": 9.473684210526315e-06, "loss": 0.26545417308807373, "step": 13 }, { "epoch": 0.006097560975609756, "grad_norm": 8.815078735351562, "learning_rate": 1.0263157894736843e-05, "loss": 0.2284773588180542, "step": 14 }, { "epoch": 0.006533101045296167, "grad_norm": 10.127286911010742, "learning_rate": 1.1052631578947368e-05, "loss": 0.31488341093063354, "step": 15 }, { "epoch": 0.006968641114982578, "grad_norm": 10.91253662109375, "learning_rate": 1.1842105263157895e-05, "loss": 0.24568629264831543, "step": 16 }, { "epoch": 0.007404181184668989, "grad_norm": 6.828537464141846, "learning_rate": 1.263157894736842e-05, "loss": 0.18750570714473724, "step": 17 }, { "epoch": 0.0078397212543554, "grad_norm": 7.178056240081787, "learning_rate": 1.3421052631578948e-05, "loss": 0.2869262993335724, "step": 18 }, { "epoch": 0.008275261324041812, "grad_norm": 6.874632358551025, "learning_rate": 1.4210526315789473e-05, "loss": 0.26060575246810913, "step": 19 }, { "epoch": 0.008710801393728223, "grad_norm": 5.87429666519165, "learning_rate": 1.5e-05, "loss": 0.1928044855594635, "step": 20 }, { "epoch": 0.009146341463414634, "grad_norm": 7.777878284454346, "learning_rate": 1.5789473684210526e-05, "loss": 0.2326163351535797, "step": 21 }, { "epoch": 0.009581881533101045, "grad_norm": 5.232192516326904, "learning_rate": 1.6578947368421053e-05, "loss": 0.2032701075077057, "step": 22 }, { "epoch": 0.010017421602787456, "grad_norm": 6.685811996459961, "learning_rate": 1.736842105263158e-05, "loss": 0.31492549180984497, "step": 23 }, { "epoch": 0.010452961672473868, "grad_norm": 4.9634785652160645, "learning_rate": 1.8157894736842107e-05, "loss": 0.2702597975730896, "step": 24 }, { "epoch": 0.01088850174216028, "grad_norm": 5.087269306182861, "learning_rate": 1.894736842105263e-05, "loss": 0.23216812312602997, "step": 25 }, { "epoch": 0.01132404181184669, "grad_norm": 5.197567462921143, "learning_rate": 1.9736842105263158e-05, "loss": 0.13799116015434265, "step": 26 }, { "epoch": 0.011759581881533102, "grad_norm": 4.029556751251221, "learning_rate": 2.0526315789473685e-05, "loss": 0.12358037382364273, "step": 27 }, { "epoch": 0.012195121951219513, "grad_norm": 5.432285308837891, "learning_rate": 2.1315789473684212e-05, "loss": 0.277026891708374, "step": 28 }, { "epoch": 0.012630662020905924, "grad_norm": 8.487820625305176, "learning_rate": 2.2105263157894736e-05, "loss": 0.30865415930747986, "step": 29 }, { "epoch": 0.013066202090592335, "grad_norm": 7.840683460235596, "learning_rate": 2.2894736842105263e-05, "loss": 0.2973104417324066, "step": 30 }, { "epoch": 0.013501742160278746, "grad_norm": 7.176794528961182, "learning_rate": 2.368421052631579e-05, "loss": 0.22405536472797394, "step": 31 }, { "epoch": 0.013937282229965157, "grad_norm": 11.020298957824707, "learning_rate": 2.4473684210526318e-05, "loss": 0.2905920743942261, "step": 32 }, { "epoch": 0.014372822299651568, "grad_norm": 7.147019863128662, "learning_rate": 2.526315789473684e-05, "loss": 0.3145636022090912, "step": 33 }, { "epoch": 0.014808362369337979, "grad_norm": 7.532826900482178, "learning_rate": 2.605263157894737e-05, "loss": 0.3344365358352661, "step": 34 }, { "epoch": 0.01524390243902439, "grad_norm": 6.241111755371094, "learning_rate": 2.6842105263157896e-05, "loss": 0.24801155924797058, "step": 35 }, { "epoch": 0.0156794425087108, "grad_norm": 8.223255157470703, "learning_rate": 2.7631578947368423e-05, "loss": 0.4269346594810486, "step": 36 }, { "epoch": 0.016114982578397212, "grad_norm": 4.365837574005127, "learning_rate": 2.8421052631578946e-05, "loss": 0.14367175102233887, "step": 37 }, { "epoch": 0.016550522648083623, "grad_norm": 5.178925037384033, "learning_rate": 2.9210526315789474e-05, "loss": 0.25906264781951904, "step": 38 }, { "epoch": 0.016986062717770034, "grad_norm": 5.43660306930542, "learning_rate": 3e-05, "loss": 0.16134388744831085, "step": 39 }, { "epoch": 0.017421602787456445, "grad_norm": 4.948673725128174, "learning_rate": 3.078947368421053e-05, "loss": 0.2457384318113327, "step": 40 }, { "epoch": 0.017857142857142856, "grad_norm": 5.907590866088867, "learning_rate": 3.157894736842105e-05, "loss": 0.2927418649196625, "step": 41 }, { "epoch": 0.018292682926829267, "grad_norm": 7.024808406829834, "learning_rate": 3.236842105263158e-05, "loss": 0.31473037600517273, "step": 42 }, { "epoch": 0.018728222996515678, "grad_norm": 5.892182350158691, "learning_rate": 3.3157894736842106e-05, "loss": 0.26015329360961914, "step": 43 }, { "epoch": 0.01916376306620209, "grad_norm": 5.649168491363525, "learning_rate": 3.394736842105263e-05, "loss": 0.3303201496601105, "step": 44 }, { "epoch": 0.0195993031358885, "grad_norm": 5.630763053894043, "learning_rate": 3.473684210526316e-05, "loss": 0.2580961585044861, "step": 45 }, { "epoch": 0.02003484320557491, "grad_norm": 4.931653022766113, "learning_rate": 3.5526315789473684e-05, "loss": 0.2730676233768463, "step": 46 }, { "epoch": 0.020470383275261322, "grad_norm": 5.711925506591797, "learning_rate": 3.6315789473684214e-05, "loss": 0.26530224084854126, "step": 47 }, { "epoch": 0.020905923344947737, "grad_norm": 5.747982978820801, "learning_rate": 3.710526315789474e-05, "loss": 0.2088877111673355, "step": 48 }, { "epoch": 0.021341463414634148, "grad_norm": 7.233992576599121, "learning_rate": 3.789473684210526e-05, "loss": 0.40417182445526123, "step": 49 }, { "epoch": 0.02177700348432056, "grad_norm": 4.631650924682617, "learning_rate": 3.868421052631579e-05, "loss": 0.2568231523036957, "step": 50 }, { "epoch": 0.02221254355400697, "grad_norm": 4.6749396324157715, "learning_rate": 3.9473684210526316e-05, "loss": 0.23617815971374512, "step": 51 }, { "epoch": 0.02264808362369338, "grad_norm": 6.705143928527832, "learning_rate": 4.026315789473684e-05, "loss": 0.18635666370391846, "step": 52 }, { "epoch": 0.023083623693379792, "grad_norm": 6.137414455413818, "learning_rate": 4.105263157894737e-05, "loss": 0.34953972697257996, "step": 53 }, { "epoch": 0.023519163763066203, "grad_norm": 5.367718696594238, "learning_rate": 4.1842105263157894e-05, "loss": 0.3586777150630951, "step": 54 }, { "epoch": 0.023954703832752614, "grad_norm": 6.1850266456604, "learning_rate": 4.2631578947368425e-05, "loss": 0.3774147927761078, "step": 55 }, { "epoch": 0.024390243902439025, "grad_norm": 6.369204044342041, "learning_rate": 4.342105263157895e-05, "loss": 0.4390595853328705, "step": 56 }, { "epoch": 0.024825783972125436, "grad_norm": 6.303933143615723, "learning_rate": 4.421052631578947e-05, "loss": 0.22120797634124756, "step": 57 }, { "epoch": 0.025261324041811847, "grad_norm": 5.297045707702637, "learning_rate": 4.5e-05, "loss": 0.25211477279663086, "step": 58 }, { "epoch": 0.02569686411149826, "grad_norm": 6.022722244262695, "learning_rate": 4.5789473684210527e-05, "loss": 0.532123327255249, "step": 59 }, { "epoch": 0.02613240418118467, "grad_norm": 6.153242111206055, "learning_rate": 4.657894736842105e-05, "loss": 0.3599899709224701, "step": 60 }, { "epoch": 0.02656794425087108, "grad_norm": 6.2072319984436035, "learning_rate": 4.736842105263158e-05, "loss": 0.45974528789520264, "step": 61 }, { "epoch": 0.02700348432055749, "grad_norm": 5.221970081329346, "learning_rate": 4.815789473684211e-05, "loss": 0.44737017154693604, "step": 62 }, { "epoch": 0.027439024390243903, "grad_norm": 6.503662109375, "learning_rate": 4.8947368421052635e-05, "loss": 0.5785658359527588, "step": 63 }, { "epoch": 0.027874564459930314, "grad_norm": 7.027008056640625, "learning_rate": 4.973684210526316e-05, "loss": 0.30538809299468994, "step": 64 }, { "epoch": 0.028310104529616725, "grad_norm": 7.643102169036865, "learning_rate": 5.052631578947368e-05, "loss": 0.49250057339668274, "step": 65 }, { "epoch": 0.028745644599303136, "grad_norm": 5.779397964477539, "learning_rate": 5.131578947368421e-05, "loss": 0.46952173113822937, "step": 66 }, { "epoch": 0.029181184668989547, "grad_norm": 12.834272384643555, "learning_rate": 5.210526315789474e-05, "loss": 0.3172321021556854, "step": 67 }, { "epoch": 0.029616724738675958, "grad_norm": 5.2291693687438965, "learning_rate": 5.289473684210526e-05, "loss": 0.4698142409324646, "step": 68 }, { "epoch": 0.03005226480836237, "grad_norm": 5.812905788421631, "learning_rate": 5.368421052631579e-05, "loss": 0.3136313259601593, "step": 69 }, { "epoch": 0.03048780487804878, "grad_norm": 5.255738735198975, "learning_rate": 5.447368421052632e-05, "loss": 0.3546884059906006, "step": 70 }, { "epoch": 0.03092334494773519, "grad_norm": 4.453991413116455, "learning_rate": 5.5263157894736845e-05, "loss": 0.24897736310958862, "step": 71 }, { "epoch": 0.0313588850174216, "grad_norm": 11.316097259521484, "learning_rate": 5.605263157894737e-05, "loss": 0.444821298122406, "step": 72 }, { "epoch": 0.031794425087108016, "grad_norm": 6.605533123016357, "learning_rate": 5.684210526315789e-05, "loss": 0.6100848913192749, "step": 73 }, { "epoch": 0.032229965156794424, "grad_norm": 7.6224565505981445, "learning_rate": 5.7631578947368423e-05, "loss": 0.37146836519241333, "step": 74 }, { "epoch": 0.03266550522648084, "grad_norm": 6.695453643798828, "learning_rate": 5.842105263157895e-05, "loss": 0.25589242577552795, "step": 75 }, { "epoch": 0.033101045296167246, "grad_norm": 7.621274471282959, "learning_rate": 5.921052631578947e-05, "loss": 0.6915152668952942, "step": 76 }, { "epoch": 0.03353658536585366, "grad_norm": 6.167173862457275, "learning_rate": 6e-05, "loss": 0.2585829198360443, "step": 77 }, { "epoch": 0.03397212543554007, "grad_norm": 8.966745376586914, "learning_rate": 5.999997533626893e-05, "loss": 0.6270936727523804, "step": 78 }, { "epoch": 0.03440766550522648, "grad_norm": 7.174211025238037, "learning_rate": 5.999990134511629e-05, "loss": 0.5994287133216858, "step": 79 }, { "epoch": 0.03484320557491289, "grad_norm": 7.08806848526001, "learning_rate": 5.999977802666372e-05, "loss": 0.3147191107273102, "step": 80 }, { "epoch": 0.035278745644599305, "grad_norm": 3.8982701301574707, "learning_rate": 5.999960538111399e-05, "loss": 0.20229943096637726, "step": 81 }, { "epoch": 0.03571428571428571, "grad_norm": 6.4147186279296875, "learning_rate": 5.999938340875098e-05, "loss": 0.5016701221466064, "step": 82 }, { "epoch": 0.03614982578397213, "grad_norm": 5.1908793449401855, "learning_rate": 5.999911210993967e-05, "loss": 0.34840095043182373, "step": 83 }, { "epoch": 0.036585365853658534, "grad_norm": 4.656551361083984, "learning_rate": 5.9998791485126134e-05, "loss": 0.2722494304180145, "step": 84 }, { "epoch": 0.03702090592334495, "grad_norm": 5.410297870635986, "learning_rate": 5.9998421534837564e-05, "loss": 0.42299941182136536, "step": 85 }, { "epoch": 0.037456445993031356, "grad_norm": 5.255926132202148, "learning_rate": 5.9998002259682246e-05, "loss": 0.5459646582603455, "step": 86 }, { "epoch": 0.03789198606271777, "grad_norm": 5.8595781326293945, "learning_rate": 5.999753366034958e-05, "loss": 0.3151801526546478, "step": 87 }, { "epoch": 0.03832752613240418, "grad_norm": 5.519594192504883, "learning_rate": 5.999701573761005e-05, "loss": 0.45058226585388184, "step": 88 }, { "epoch": 0.03876306620209059, "grad_norm": 4.478116989135742, "learning_rate": 5.999644849231526e-05, "loss": 0.45803558826446533, "step": 89 }, { "epoch": 0.039198606271777, "grad_norm": 10.494302749633789, "learning_rate": 5.99958319253979e-05, "loss": 0.6166162490844727, "step": 90 }, { "epoch": 0.039634146341463415, "grad_norm": 6.683266639709473, "learning_rate": 5.999516603787175e-05, "loss": 0.7317699193954468, "step": 91 }, { "epoch": 0.04006968641114982, "grad_norm": 4.745250701904297, "learning_rate": 5.99944508308317e-05, "loss": 0.2565714418888092, "step": 92 }, { "epoch": 0.04050522648083624, "grad_norm": 5.142008304595947, "learning_rate": 5.999368630545374e-05, "loss": 0.3202317953109741, "step": 93 }, { "epoch": 0.040940766550522645, "grad_norm": 5.019248962402344, "learning_rate": 5.999287246299492e-05, "loss": 0.43142205476760864, "step": 94 }, { "epoch": 0.04137630662020906, "grad_norm": 4.156179904937744, "learning_rate": 5.999200930479341e-05, "loss": 0.34984830021858215, "step": 95 }, { "epoch": 0.041811846689895474, "grad_norm": 4.465534687042236, "learning_rate": 5.9991096832268456e-05, "loss": 0.3629593551158905, "step": 96 }, { "epoch": 0.04224738675958188, "grad_norm": 4.149345397949219, "learning_rate": 5.9990135046920397e-05, "loss": 0.30301085114479065, "step": 97 }, { "epoch": 0.042682926829268296, "grad_norm": 7.968324661254883, "learning_rate": 5.9989123950330635e-05, "loss": 0.34854352474212646, "step": 98 }, { "epoch": 0.043118466898954703, "grad_norm": 4.874617576599121, "learning_rate": 5.998806354416167e-05, "loss": 0.34224873781204224, "step": 99 }, { "epoch": 0.04355400696864112, "grad_norm": 5.08293342590332, "learning_rate": 5.9986953830157074e-05, "loss": 0.48989981412887573, "step": 100 }, { "epoch": 0.043989547038327526, "grad_norm": 4.008183479309082, "learning_rate": 5.9985794810141485e-05, "loss": 0.29492127895355225, "step": 101 }, { "epoch": 0.04442508710801394, "grad_norm": 5.573810577392578, "learning_rate": 5.998458648602064e-05, "loss": 0.6134231686592102, "step": 102 }, { "epoch": 0.04486062717770035, "grad_norm": 9.695103645324707, "learning_rate": 5.99833288597813e-05, "loss": 0.4994890093803406, "step": 103 }, { "epoch": 0.04529616724738676, "grad_norm": 5.72934103012085, "learning_rate": 5.9982021933491335e-05, "loss": 0.49891799688339233, "step": 104 }, { "epoch": 0.04573170731707317, "grad_norm": 4.611719608306885, "learning_rate": 5.998066570929964e-05, "loss": 0.40656140446662903, "step": 105 }, { "epoch": 0.046167247386759584, "grad_norm": 4.542270660400391, "learning_rate": 5.99792601894362e-05, "loss": 0.3569484353065491, "step": 106 }, { "epoch": 0.04660278745644599, "grad_norm": 5.533016204833984, "learning_rate": 5.997780537621203e-05, "loss": 0.4485136568546295, "step": 107 }, { "epoch": 0.047038327526132406, "grad_norm": 5.8837809562683105, "learning_rate": 5.997630127201921e-05, "loss": 0.35450878739356995, "step": 108 }, { "epoch": 0.047473867595818814, "grad_norm": 4.73000955581665, "learning_rate": 5.997474787933086e-05, "loss": 0.40301626920700073, "step": 109 }, { "epoch": 0.04790940766550523, "grad_norm": 5.76838493347168, "learning_rate": 5.997314520070114e-05, "loss": 0.4599734842777252, "step": 110 }, { "epoch": 0.048344947735191636, "grad_norm": 5.2645416259765625, "learning_rate": 5.997149323876525e-05, "loss": 0.3353433609008789, "step": 111 }, { "epoch": 0.04878048780487805, "grad_norm": 4.870075702667236, "learning_rate": 5.9969791996239446e-05, "loss": 0.41569170355796814, "step": 112 }, { "epoch": 0.04921602787456446, "grad_norm": 3.8678648471832275, "learning_rate": 5.996804147592097e-05, "loss": 0.23164506256580353, "step": 113 }, { "epoch": 0.04965156794425087, "grad_norm": 4.406476974487305, "learning_rate": 5.996624168068812e-05, "loss": 0.29653680324554443, "step": 114 }, { "epoch": 0.05008710801393728, "grad_norm": 4.233344078063965, "learning_rate": 5.996439261350021e-05, "loss": 0.41761860251426697, "step": 115 }, { "epoch": 0.050522648083623695, "grad_norm": 4.935632228851318, "learning_rate": 5.996249427739757e-05, "loss": 0.48940780758857727, "step": 116 }, { "epoch": 0.0509581881533101, "grad_norm": 9.252951622009277, "learning_rate": 5.9960546675501534e-05, "loss": 0.520698070526123, "step": 117 }, { "epoch": 0.05139372822299652, "grad_norm": 5.8596577644348145, "learning_rate": 5.995854981101444e-05, "loss": 0.34946513175964355, "step": 118 }, { "epoch": 0.051829268292682924, "grad_norm": 5.224259376525879, "learning_rate": 5.995650368721963e-05, "loss": 0.24262261390686035, "step": 119 }, { "epoch": 0.05226480836236934, "grad_norm": 4.012600898742676, "learning_rate": 5.995440830748144e-05, "loss": 0.2619999945163727, "step": 120 }, { "epoch": 0.052700348432055746, "grad_norm": 28.5828800201416, "learning_rate": 5.99522636752452e-05, "loss": 0.6061434745788574, "step": 121 }, { "epoch": 0.05313588850174216, "grad_norm": 7.685927391052246, "learning_rate": 5.995006979403723e-05, "loss": 0.41815459728240967, "step": 122 }, { "epoch": 0.05357142857142857, "grad_norm": 4.344602108001709, "learning_rate": 5.994782666746479e-05, "loss": 0.35912615060806274, "step": 123 }, { "epoch": 0.05400696864111498, "grad_norm": 7.120609760284424, "learning_rate": 5.994553429921616e-05, "loss": 0.5070939660072327, "step": 124 }, { "epoch": 0.05444250871080139, "grad_norm": 5.132368564605713, "learning_rate": 5.994319269306055e-05, "loss": 0.2924511432647705, "step": 125 }, { "epoch": 0.054878048780487805, "grad_norm": 3.984788179397583, "learning_rate": 5.994080185284815e-05, "loss": 0.44720563292503357, "step": 126 }, { "epoch": 0.05531358885017421, "grad_norm": 4.1977458000183105, "learning_rate": 5.993836178251009e-05, "loss": 0.32531148195266724, "step": 127 }, { "epoch": 0.05574912891986063, "grad_norm": 4.624279022216797, "learning_rate": 5.9935872486058466e-05, "loss": 0.3639815151691437, "step": 128 }, { "epoch": 0.05618466898954704, "grad_norm": 5.961254119873047, "learning_rate": 5.993333396758628e-05, "loss": 0.34735050797462463, "step": 129 }, { "epoch": 0.05662020905923345, "grad_norm": 4.802722930908203, "learning_rate": 5.993074623126751e-05, "loss": 0.5503559112548828, "step": 130 }, { "epoch": 0.057055749128919864, "grad_norm": 5.496182918548584, "learning_rate": 5.992810928135702e-05, "loss": 0.3910374641418457, "step": 131 }, { "epoch": 0.05749128919860627, "grad_norm": 4.28236722946167, "learning_rate": 5.992542312219062e-05, "loss": 0.5372604727745056, "step": 132 }, { "epoch": 0.057926829268292686, "grad_norm": 3.513167142868042, "learning_rate": 5.9922687758185025e-05, "loss": 0.24906368553638458, "step": 133 }, { "epoch": 0.05836236933797909, "grad_norm": 4.407099723815918, "learning_rate": 5.991990319383784e-05, "loss": 0.2458866685628891, "step": 134 }, { "epoch": 0.05879790940766551, "grad_norm": 3.931243658065796, "learning_rate": 5.991706943372761e-05, "loss": 0.4201250374317169, "step": 135 }, { "epoch": 0.059233449477351915, "grad_norm": 4.789584159851074, "learning_rate": 5.991418648251372e-05, "loss": 0.32899245619773865, "step": 136 }, { "epoch": 0.05966898954703833, "grad_norm": 4.8763041496276855, "learning_rate": 5.991125434493646e-05, "loss": 0.2878221869468689, "step": 137 }, { "epoch": 0.06010452961672474, "grad_norm": 3.938612461090088, "learning_rate": 5.990827302581699e-05, "loss": 0.4039849042892456, "step": 138 }, { "epoch": 0.06054006968641115, "grad_norm": 5.274370193481445, "learning_rate": 5.990524253005736e-05, "loss": 0.605360209941864, "step": 139 }, { "epoch": 0.06097560975609756, "grad_norm": 5.30519962310791, "learning_rate": 5.990216286264044e-05, "loss": 0.45326894521713257, "step": 140 }, { "epoch": 0.061411149825783974, "grad_norm": 5.347064018249512, "learning_rate": 5.9899034028629974e-05, "loss": 0.6441291570663452, "step": 141 }, { "epoch": 0.06184668989547038, "grad_norm": 3.7961628437042236, "learning_rate": 5.9895856033170545e-05, "loss": 0.33006763458251953, "step": 142 }, { "epoch": 0.062282229965156796, "grad_norm": 4.970699787139893, "learning_rate": 5.989262888148757e-05, "loss": 0.4621412456035614, "step": 143 }, { "epoch": 0.0627177700348432, "grad_norm": 3.839979648590088, "learning_rate": 5.9889352578887285e-05, "loss": 0.4416477680206299, "step": 144 }, { "epoch": 0.06315331010452961, "grad_norm": 4.4527482986450195, "learning_rate": 5.988602713075675e-05, "loss": 0.3810202181339264, "step": 145 }, { "epoch": 0.06358885017421603, "grad_norm": 4.3594136238098145, "learning_rate": 5.988265254256383e-05, "loss": 0.5155733823776245, "step": 146 }, { "epoch": 0.06402439024390244, "grad_norm": 3.899627923965454, "learning_rate": 5.987922881985718e-05, "loss": 0.5186405777931213, "step": 147 }, { "epoch": 0.06445993031358885, "grad_norm": 4.210773944854736, "learning_rate": 5.987575596826625e-05, "loss": 0.37238413095474243, "step": 148 }, { "epoch": 0.06489547038327526, "grad_norm": 7.1049370765686035, "learning_rate": 5.9872233993501284e-05, "loss": 0.44268158078193665, "step": 149 }, { "epoch": 0.06533101045296168, "grad_norm": 5.073590278625488, "learning_rate": 5.986866290135327e-05, "loss": 0.4634779095649719, "step": 150 }, { "epoch": 0.06576655052264808, "grad_norm": 4.059816837310791, "learning_rate": 5.986504269769399e-05, "loss": 0.27338430285453796, "step": 151 }, { "epoch": 0.06620209059233449, "grad_norm": 4.310779571533203, "learning_rate": 5.986137338847595e-05, "loss": 0.4411619007587433, "step": 152 }, { "epoch": 0.0666376306620209, "grad_norm": 3.5691351890563965, "learning_rate": 5.9857654979732404e-05, "loss": 0.19724196195602417, "step": 153 }, { "epoch": 0.06707317073170732, "grad_norm": 5.597500324249268, "learning_rate": 5.985388747757734e-05, "loss": 0.4121205806732178, "step": 154 }, { "epoch": 0.06750871080139373, "grad_norm": 3.7421982288360596, "learning_rate": 5.985007088820547e-05, "loss": 0.37780073285102844, "step": 155 }, { "epoch": 0.06794425087108014, "grad_norm": 3.0510623455047607, "learning_rate": 5.984620521789223e-05, "loss": 0.33326056599617004, "step": 156 }, { "epoch": 0.06837979094076654, "grad_norm": 5.448624134063721, "learning_rate": 5.984229047299372e-05, "loss": 0.30908840894699097, "step": 157 }, { "epoch": 0.06881533101045297, "grad_norm": 25.528583526611328, "learning_rate": 5.983832665994678e-05, "loss": 0.9894929528236389, "step": 158 }, { "epoch": 0.06925087108013937, "grad_norm": 3.450305700302124, "learning_rate": 5.9834313785268876e-05, "loss": 0.25326600670814514, "step": 159 }, { "epoch": 0.06968641114982578, "grad_norm": 8.0743408203125, "learning_rate": 5.9830251855558186e-05, "loss": 0.4455889165401459, "step": 160 }, { "epoch": 0.0701219512195122, "grad_norm": 4.482630729675293, "learning_rate": 5.982614087749354e-05, "loss": 0.31729862093925476, "step": 161 }, { "epoch": 0.07055749128919861, "grad_norm": 3.542126417160034, "learning_rate": 5.982198085783441e-05, "loss": 0.41243883967399597, "step": 162 }, { "epoch": 0.07099303135888502, "grad_norm": 6.5717244148254395, "learning_rate": 5.981777180342089e-05, "loss": 0.5788612961769104, "step": 163 }, { "epoch": 0.07142857142857142, "grad_norm": 4.794477939605713, "learning_rate": 5.981351372117371e-05, "loss": 0.448479026556015, "step": 164 }, { "epoch": 0.07186411149825785, "grad_norm": 3.567678689956665, "learning_rate": 5.980920661809424e-05, "loss": 0.29112547636032104, "step": 165 }, { "epoch": 0.07229965156794425, "grad_norm": 5.347809314727783, "learning_rate": 5.98048505012644e-05, "loss": 0.5111991763114929, "step": 166 }, { "epoch": 0.07273519163763066, "grad_norm": 5.480915069580078, "learning_rate": 5.980044537784675e-05, "loss": 0.4717521369457245, "step": 167 }, { "epoch": 0.07317073170731707, "grad_norm": 4.314980506896973, "learning_rate": 5.9795991255084396e-05, "loss": 0.670697033405304, "step": 168 }, { "epoch": 0.07360627177700349, "grad_norm": 4.50567102432251, "learning_rate": 5.9791488140301025e-05, "loss": 0.6572335362434387, "step": 169 }, { "epoch": 0.0740418118466899, "grad_norm": 3.9728336334228516, "learning_rate": 5.9786936040900883e-05, "loss": 0.4115130305290222, "step": 170 }, { "epoch": 0.0744773519163763, "grad_norm": 4.734399795532227, "learning_rate": 5.9782334964368754e-05, "loss": 0.730222761631012, "step": 171 }, { "epoch": 0.07491289198606271, "grad_norm": 4.3242011070251465, "learning_rate": 5.9777684918269954e-05, "loss": 0.5822874307632446, "step": 172 }, { "epoch": 0.07534843205574913, "grad_norm": 3.332104444503784, "learning_rate": 5.977298591025031e-05, "loss": 0.3016602098941803, "step": 173 }, { "epoch": 0.07578397212543554, "grad_norm": 3.616602897644043, "learning_rate": 5.9768237948036154e-05, "loss": 0.29622113704681396, "step": 174 }, { "epoch": 0.07621951219512195, "grad_norm": 4.338099956512451, "learning_rate": 5.976344103943434e-05, "loss": 0.5108498930931091, "step": 175 }, { "epoch": 0.07665505226480836, "grad_norm": 24.313859939575195, "learning_rate": 5.975859519233215e-05, "loss": 0.5016686320304871, "step": 176 }, { "epoch": 0.07709059233449478, "grad_norm": 3.768911123275757, "learning_rate": 5.975370041469738e-05, "loss": 0.39636003971099854, "step": 177 }, { "epoch": 0.07752613240418119, "grad_norm": 6.764847278594971, "learning_rate": 5.974875671457827e-05, "loss": 0.4613531231880188, "step": 178 }, { "epoch": 0.0779616724738676, "grad_norm": 4.90284538269043, "learning_rate": 5.974376410010347e-05, "loss": 0.16952866315841675, "step": 179 }, { "epoch": 0.078397212543554, "grad_norm": 3.6416501998901367, "learning_rate": 5.9738722579482085e-05, "loss": 0.442071795463562, "step": 180 }, { "epoch": 0.07883275261324042, "grad_norm": 3.841498613357544, "learning_rate": 5.9733632161003644e-05, "loss": 0.3613032102584839, "step": 181 }, { "epoch": 0.07926829268292683, "grad_norm": 3.3739707469940186, "learning_rate": 5.9728492853038046e-05, "loss": 0.3872697651386261, "step": 182 }, { "epoch": 0.07970383275261324, "grad_norm": 3.3486735820770264, "learning_rate": 5.97233046640356e-05, "loss": 0.2394520789384842, "step": 183 }, { "epoch": 0.08013937282229965, "grad_norm": 3.3529720306396484, "learning_rate": 5.971806760252697e-05, "loss": 0.24202373623847961, "step": 184 }, { "epoch": 0.08057491289198607, "grad_norm": 6.825578689575195, "learning_rate": 5.97127816771232e-05, "loss": 0.3372780382633209, "step": 185 }, { "epoch": 0.08101045296167247, "grad_norm": 4.4420671463012695, "learning_rate": 5.970744689651566e-05, "loss": 0.6656676530838013, "step": 186 }, { "epoch": 0.08144599303135888, "grad_norm": 3.852478265762329, "learning_rate": 5.970206326947606e-05, "loss": 0.558366596698761, "step": 187 }, { "epoch": 0.08188153310104529, "grad_norm": 2.8650240898132324, "learning_rate": 5.9696630804856415e-05, "loss": 0.29067957401275635, "step": 188 }, { "epoch": 0.08231707317073171, "grad_norm": 3.5653297901153564, "learning_rate": 5.9691149511589044e-05, "loss": 0.3298783600330353, "step": 189 }, { "epoch": 0.08275261324041812, "grad_norm": 4.125470161437988, "learning_rate": 5.968561939868658e-05, "loss": 0.4376567006111145, "step": 190 }, { "epoch": 0.08318815331010453, "grad_norm": 3.92022967338562, "learning_rate": 5.9680040475241876e-05, "loss": 0.3284645676612854, "step": 191 }, { "epoch": 0.08362369337979095, "grad_norm": 3.5128839015960693, "learning_rate": 5.9674412750428086e-05, "loss": 0.32722342014312744, "step": 192 }, { "epoch": 0.08405923344947736, "grad_norm": 3.4035446643829346, "learning_rate": 5.966873623349859e-05, "loss": 0.19320723414421082, "step": 193 }, { "epoch": 0.08449477351916376, "grad_norm": 2.8215816020965576, "learning_rate": 5.9663010933786985e-05, "loss": 0.23085403442382812, "step": 194 }, { "epoch": 0.08493031358885017, "grad_norm": 3.409130334854126, "learning_rate": 5.9657236860707095e-05, "loss": 0.27380236983299255, "step": 195 }, { "epoch": 0.08536585365853659, "grad_norm": 3.850834608078003, "learning_rate": 5.9651414023752926e-05, "loss": 0.5454622507095337, "step": 196 }, { "epoch": 0.085801393728223, "grad_norm": 8.392861366271973, "learning_rate": 5.9645542432498674e-05, "loss": 0.5527616143226624, "step": 197 }, { "epoch": 0.08623693379790941, "grad_norm": 3.055513858795166, "learning_rate": 5.96396220965987e-05, "loss": 0.22095486521720886, "step": 198 }, { "epoch": 0.08667247386759581, "grad_norm": 4.779624938964844, "learning_rate": 5.9633653025787494e-05, "loss": 0.5306509733200073, "step": 199 }, { "epoch": 0.08710801393728224, "grad_norm": 5.780481815338135, "learning_rate": 5.9627635229879714e-05, "loss": 0.6932032704353333, "step": 200 }, { "epoch": 0.08754355400696864, "grad_norm": 4.153634071350098, "learning_rate": 5.96215687187701e-05, "loss": 0.3226391077041626, "step": 201 }, { "epoch": 0.08797909407665505, "grad_norm": 4.055916786193848, "learning_rate": 5.961545350243351e-05, "loss": 0.3141464293003082, "step": 202 }, { "epoch": 0.08841463414634146, "grad_norm": 4.628835201263428, "learning_rate": 5.9609289590924874e-05, "loss": 0.4275514483451843, "step": 203 }, { "epoch": 0.08885017421602788, "grad_norm": 3.744318723678589, "learning_rate": 5.960307699437921e-05, "loss": 0.46349039673805237, "step": 204 }, { "epoch": 0.08928571428571429, "grad_norm": 3.325406074523926, "learning_rate": 5.959681572301154e-05, "loss": 0.5422636866569519, "step": 205 }, { "epoch": 0.0897212543554007, "grad_norm": 3.6108150482177734, "learning_rate": 5.959050578711699e-05, "loss": 0.34997403621673584, "step": 206 }, { "epoch": 0.0901567944250871, "grad_norm": 3.3761067390441895, "learning_rate": 5.9584147197070644e-05, "loss": 0.22484757006168365, "step": 207 }, { "epoch": 0.09059233449477352, "grad_norm": 5.039508819580078, "learning_rate": 5.957773996332762e-05, "loss": 0.6595714688301086, "step": 208 }, { "epoch": 0.09102787456445993, "grad_norm": 3.130208730697632, "learning_rate": 5.957128409642299e-05, "loss": 0.2467401921749115, "step": 209 }, { "epoch": 0.09146341463414634, "grad_norm": 2.3789288997650146, "learning_rate": 5.95647796069718e-05, "loss": 0.20558048784732819, "step": 210 }, { "epoch": 0.09189895470383275, "grad_norm": 4.2998528480529785, "learning_rate": 5.955822650566907e-05, "loss": 0.4207920432090759, "step": 211 }, { "epoch": 0.09233449477351917, "grad_norm": 5.529782772064209, "learning_rate": 5.9551624803289706e-05, "loss": 0.7910427451133728, "step": 212 }, { "epoch": 0.09277003484320558, "grad_norm": 4.337933540344238, "learning_rate": 5.954497451068856e-05, "loss": 0.4066309630870819, "step": 213 }, { "epoch": 0.09320557491289198, "grad_norm": 4.27602481842041, "learning_rate": 5.953827563880037e-05, "loss": 0.4262276887893677, "step": 214 }, { "epoch": 0.09364111498257839, "grad_norm": 3.751633644104004, "learning_rate": 5.953152819863974e-05, "loss": 0.13259102404117584, "step": 215 }, { "epoch": 0.09407665505226481, "grad_norm": 4.1712260246276855, "learning_rate": 5.9524732201301144e-05, "loss": 0.41622844338417053, "step": 216 }, { "epoch": 0.09451219512195122, "grad_norm": 4.062272548675537, "learning_rate": 5.951788765795889e-05, "loss": 0.3765306770801544, "step": 217 }, { "epoch": 0.09494773519163763, "grad_norm": 3.4402194023132324, "learning_rate": 5.951099457986712e-05, "loss": 0.41485047340393066, "step": 218 }, { "epoch": 0.09538327526132404, "grad_norm": 3.8705575466156006, "learning_rate": 5.950405297835975e-05, "loss": 0.744124710559845, "step": 219 }, { "epoch": 0.09581881533101046, "grad_norm": 4.074329376220703, "learning_rate": 5.949706286485051e-05, "loss": 0.47809547185897827, "step": 220 }, { "epoch": 0.09625435540069686, "grad_norm": 2.601438522338867, "learning_rate": 5.949002425083289e-05, "loss": 0.25259143114089966, "step": 221 }, { "epoch": 0.09668989547038327, "grad_norm": 3.029209852218628, "learning_rate": 5.9482937147880115e-05, "loss": 0.24662332236766815, "step": 222 }, { "epoch": 0.09712543554006968, "grad_norm": 4.5319294929504395, "learning_rate": 5.9475801567645154e-05, "loss": 0.553925096988678, "step": 223 }, { "epoch": 0.0975609756097561, "grad_norm": 3.651581048965454, "learning_rate": 5.9468617521860666e-05, "loss": 0.38856908679008484, "step": 224 }, { "epoch": 0.09799651567944251, "grad_norm": 4.415187835693359, "learning_rate": 5.946138502233901e-05, "loss": 0.262853741645813, "step": 225 }, { "epoch": 0.09843205574912892, "grad_norm": 3.820777416229248, "learning_rate": 5.945410408097221e-05, "loss": 0.4125519394874573, "step": 226 }, { "epoch": 0.09886759581881534, "grad_norm": 26.099712371826172, "learning_rate": 5.944677470973196e-05, "loss": 0.2600629925727844, "step": 227 }, { "epoch": 0.09930313588850175, "grad_norm": 4.106088638305664, "learning_rate": 5.943939692066956e-05, "loss": 0.3799162209033966, "step": 228 }, { "epoch": 0.09973867595818815, "grad_norm": 3.5217361450195312, "learning_rate": 5.943197072591594e-05, "loss": 0.4515937268733978, "step": 229 }, { "epoch": 0.10017421602787456, "grad_norm": 4.781862258911133, "learning_rate": 5.942449613768158e-05, "loss": 0.414560467004776, "step": 230 }, { "epoch": 0.10060975609756098, "grad_norm": 4.576272010803223, "learning_rate": 5.941697316825661e-05, "loss": 0.5281628370285034, "step": 231 }, { "epoch": 0.10104529616724739, "grad_norm": 3.8092219829559326, "learning_rate": 5.940940183001062e-05, "loss": 0.1876661628484726, "step": 232 }, { "epoch": 0.1014808362369338, "grad_norm": 6.050763130187988, "learning_rate": 5.940178213539279e-05, "loss": 0.5996348857879639, "step": 233 }, { "epoch": 0.1019163763066202, "grad_norm": 4.08701229095459, "learning_rate": 5.939411409693181e-05, "loss": 0.42441272735595703, "step": 234 }, { "epoch": 0.10235191637630663, "grad_norm": 23.136457443237305, "learning_rate": 5.938639772723581e-05, "loss": 0.44853517413139343, "step": 235 }, { "epoch": 0.10278745644599303, "grad_norm": 3.8539414405822754, "learning_rate": 5.937863303899244e-05, "loss": 0.40238991379737854, "step": 236 }, { "epoch": 0.10322299651567944, "grad_norm": 3.4291346073150635, "learning_rate": 5.937082004496879e-05, "loss": 0.43223151564598083, "step": 237 }, { "epoch": 0.10365853658536585, "grad_norm": 4.153804302215576, "learning_rate": 5.936295875801135e-05, "loss": 0.2871413230895996, "step": 238 }, { "epoch": 0.10409407665505227, "grad_norm": 4.158131122589111, "learning_rate": 5.935504919104602e-05, "loss": 0.4195539057254791, "step": 239 }, { "epoch": 0.10452961672473868, "grad_norm": 4.2054924964904785, "learning_rate": 5.934709135707812e-05, "loss": 0.41957569122314453, "step": 240 }, { "epoch": 0.10496515679442509, "grad_norm": 5.174735069274902, "learning_rate": 5.9339085269192297e-05, "loss": 0.4768425524234772, "step": 241 }, { "epoch": 0.10540069686411149, "grad_norm": 3.6339337825775146, "learning_rate": 5.933103094055255e-05, "loss": 0.43883439898490906, "step": 242 }, { "epoch": 0.10583623693379791, "grad_norm": 3.986072063446045, "learning_rate": 5.932292838440219e-05, "loss": 0.5161284804344177, "step": 243 }, { "epoch": 0.10627177700348432, "grad_norm": 4.491393089294434, "learning_rate": 5.931477761406386e-05, "loss": 0.279838889837265, "step": 244 }, { "epoch": 0.10670731707317073, "grad_norm": 3.6689412593841553, "learning_rate": 5.930657864293943e-05, "loss": 0.41032958030700684, "step": 245 }, { "epoch": 0.10714285714285714, "grad_norm": 6.117321491241455, "learning_rate": 5.929833148451006e-05, "loss": 0.21936632692813873, "step": 246 }, { "epoch": 0.10757839721254356, "grad_norm": 9.828569412231445, "learning_rate": 5.9290036152336126e-05, "loss": 0.4434066414833069, "step": 247 }, { "epoch": 0.10801393728222997, "grad_norm": 3.723280191421509, "learning_rate": 5.928169266005722e-05, "loss": 0.2267613261938095, "step": 248 }, { "epoch": 0.10844947735191637, "grad_norm": 3.717986583709717, "learning_rate": 5.927330102139211e-05, "loss": 0.7076844573020935, "step": 249 }, { "epoch": 0.10888501742160278, "grad_norm": 3.0444395542144775, "learning_rate": 5.926486125013875e-05, "loss": 0.2787216603755951, "step": 250 }, { "epoch": 0.1093205574912892, "grad_norm": 10.31541919708252, "learning_rate": 5.9256373360174215e-05, "loss": 0.39915427565574646, "step": 251 }, { "epoch": 0.10975609756097561, "grad_norm": 3.321547269821167, "learning_rate": 5.924783736545471e-05, "loss": 0.24315430223941803, "step": 252 }, { "epoch": 0.11019163763066202, "grad_norm": 3.1179211139678955, "learning_rate": 5.923925328001553e-05, "loss": 0.1516541838645935, "step": 253 }, { "epoch": 0.11062717770034843, "grad_norm": 3.3325746059417725, "learning_rate": 5.9230621117971055e-05, "loss": 0.39757847785949707, "step": 254 }, { "epoch": 0.11106271777003485, "grad_norm": 2.9964897632598877, "learning_rate": 5.92219408935147e-05, "loss": 0.2858999967575073, "step": 255 }, { "epoch": 0.11149825783972125, "grad_norm": 4.240176200866699, "learning_rate": 5.9213212620918915e-05, "loss": 0.4097846448421478, "step": 256 }, { "epoch": 0.11193379790940766, "grad_norm": 3.143634080886841, "learning_rate": 5.9204436314535145e-05, "loss": 0.3486226499080658, "step": 257 }, { "epoch": 0.11236933797909408, "grad_norm": 3.751833915710449, "learning_rate": 5.9195611988793834e-05, "loss": 0.2703690528869629, "step": 258 }, { "epoch": 0.11280487804878049, "grad_norm": 2.8497073650360107, "learning_rate": 5.918673965820435e-05, "loss": 0.3483740985393524, "step": 259 }, { "epoch": 0.1132404181184669, "grad_norm": 3.8466384410858154, "learning_rate": 5.917781933735503e-05, "loss": 0.49914324283599854, "step": 260 }, { "epoch": 0.1136759581881533, "grad_norm": 3.848766565322876, "learning_rate": 5.916885104091309e-05, "loss": 0.48484426736831665, "step": 261 }, { "epoch": 0.11411149825783973, "grad_norm": 53.641883850097656, "learning_rate": 5.915983478362464e-05, "loss": 0.5588650107383728, "step": 262 }, { "epoch": 0.11454703832752614, "grad_norm": 3.2413623332977295, "learning_rate": 5.915077058031465e-05, "loss": 0.3975299596786499, "step": 263 }, { "epoch": 0.11498257839721254, "grad_norm": 5.507150173187256, "learning_rate": 5.914165844588693e-05, "loss": 0.28446516394615173, "step": 264 }, { "epoch": 0.11541811846689895, "grad_norm": 3.687784433364868, "learning_rate": 5.91324983953241e-05, "loss": 0.22974251210689545, "step": 265 }, { "epoch": 0.11585365853658537, "grad_norm": 3.8906285762786865, "learning_rate": 5.912329044368754e-05, "loss": 0.4539046287536621, "step": 266 }, { "epoch": 0.11628919860627178, "grad_norm": 3.03236985206604, "learning_rate": 5.911403460611744e-05, "loss": 0.3238216042518616, "step": 267 }, { "epoch": 0.11672473867595819, "grad_norm": 3.8074209690093994, "learning_rate": 5.910473089783268e-05, "loss": 0.4562893807888031, "step": 268 }, { "epoch": 0.1171602787456446, "grad_norm": 2.949838399887085, "learning_rate": 5.909537933413088e-05, "loss": 0.2538418173789978, "step": 269 }, { "epoch": 0.11759581881533102, "grad_norm": 3.5550177097320557, "learning_rate": 5.908597993038833e-05, "loss": 0.30767640471458435, "step": 270 }, { "epoch": 0.11803135888501742, "grad_norm": 5.034956932067871, "learning_rate": 5.9076532702059996e-05, "loss": 0.27341094613075256, "step": 271 }, { "epoch": 0.11846689895470383, "grad_norm": 3.447186231613159, "learning_rate": 5.906703766467946e-05, "loss": 0.43015486001968384, "step": 272 }, { "epoch": 0.11890243902439024, "grad_norm": 2.623302698135376, "learning_rate": 5.9057494833858934e-05, "loss": 0.35072818398475647, "step": 273 }, { "epoch": 0.11933797909407666, "grad_norm": 1.9780162572860718, "learning_rate": 5.904790422528921e-05, "loss": 0.2096354216337204, "step": 274 }, { "epoch": 0.11977351916376307, "grad_norm": 4.384994029998779, "learning_rate": 5.903826585473962e-05, "loss": 0.6722011566162109, "step": 275 }, { "epoch": 0.12020905923344948, "grad_norm": 3.368285894393921, "learning_rate": 5.902857973805805e-05, "loss": 0.420385479927063, "step": 276 }, { "epoch": 0.12064459930313588, "grad_norm": 3.893756628036499, "learning_rate": 5.901884589117089e-05, "loss": 0.5444890260696411, "step": 277 }, { "epoch": 0.1210801393728223, "grad_norm": 3.9243831634521484, "learning_rate": 5.900906433008299e-05, "loss": 0.5945472717285156, "step": 278 }, { "epoch": 0.12151567944250871, "grad_norm": 3.144181966781616, "learning_rate": 5.899923507087769e-05, "loss": 0.48838314414024353, "step": 279 }, { "epoch": 0.12195121951219512, "grad_norm": 3.3676986694335938, "learning_rate": 5.898935812971672e-05, "loss": 0.30420905351638794, "step": 280 }, { "epoch": 0.12238675958188153, "grad_norm": 2.8812191486358643, "learning_rate": 5.897943352284024e-05, "loss": 0.12117484956979752, "step": 281 }, { "epoch": 0.12282229965156795, "grad_norm": 3.402890920639038, "learning_rate": 5.896946126656677e-05, "loss": 0.35500258207321167, "step": 282 }, { "epoch": 0.12325783972125436, "grad_norm": 3.255955457687378, "learning_rate": 5.895944137729317e-05, "loss": 0.3618396818637848, "step": 283 }, { "epoch": 0.12369337979094076, "grad_norm": 3.5595552921295166, "learning_rate": 5.894937387149464e-05, "loss": 0.32178887724876404, "step": 284 }, { "epoch": 0.12412891986062717, "grad_norm": 7.080356597900391, "learning_rate": 5.893925876572467e-05, "loss": 0.9547200202941895, "step": 285 }, { "epoch": 0.12456445993031359, "grad_norm": 2.9700067043304443, "learning_rate": 5.892909607661499e-05, "loss": 0.30830103158950806, "step": 286 }, { "epoch": 0.125, "grad_norm": 3.487654209136963, "learning_rate": 5.8918885820875596e-05, "loss": 0.5279611945152283, "step": 287 }, { "epoch": 0.1254355400696864, "grad_norm": 2.330852746963501, "learning_rate": 5.89086280152947e-05, "loss": 0.21217352151870728, "step": 288 }, { "epoch": 0.12587108013937282, "grad_norm": 8.291617393493652, "learning_rate": 5.889832267673868e-05, "loss": 0.6116448640823364, "step": 289 }, { "epoch": 0.12630662020905922, "grad_norm": 2.4565370082855225, "learning_rate": 5.888796982215207e-05, "loss": 0.13923649489879608, "step": 290 }, { "epoch": 0.12674216027874566, "grad_norm": 2.9344496726989746, "learning_rate": 5.887756946855755e-05, "loss": 0.3439269959926605, "step": 291 }, { "epoch": 0.12717770034843207, "grad_norm": 3.047532796859741, "learning_rate": 5.8867121633055865e-05, "loss": 0.3120923638343811, "step": 292 }, { "epoch": 0.12761324041811847, "grad_norm": 3.0953640937805176, "learning_rate": 5.8856626332825875e-05, "loss": 0.44614851474761963, "step": 293 }, { "epoch": 0.12804878048780488, "grad_norm": 6.419539928436279, "learning_rate": 5.884608358512447e-05, "loss": 0.5056896209716797, "step": 294 }, { "epoch": 0.1284843205574913, "grad_norm": 2.7036960124969482, "learning_rate": 5.8835493407286526e-05, "loss": 0.2922249436378479, "step": 295 }, { "epoch": 0.1289198606271777, "grad_norm": 2.4225053787231445, "learning_rate": 5.882485581672495e-05, "loss": 0.18315936625003815, "step": 296 }, { "epoch": 0.1293554006968641, "grad_norm": 3.148970365524292, "learning_rate": 5.881417083093058e-05, "loss": 0.37226563692092896, "step": 297 }, { "epoch": 0.1297909407665505, "grad_norm": 4.340565204620361, "learning_rate": 5.880343846747219e-05, "loss": 0.5254518389701843, "step": 298 }, { "epoch": 0.13022648083623695, "grad_norm": 3.2641384601593018, "learning_rate": 5.8792658743996447e-05, "loss": 0.46655771136283875, "step": 299 }, { "epoch": 0.13066202090592335, "grad_norm": 4.538827896118164, "learning_rate": 5.878183167822791e-05, "loss": 0.6459740400314331, "step": 300 }, { "epoch": 0.13109756097560976, "grad_norm": 3.9605119228363037, "learning_rate": 5.877095728796897e-05, "loss": 0.5029232501983643, "step": 301 }, { "epoch": 0.13153310104529617, "grad_norm": 3.8765976428985596, "learning_rate": 5.876003559109982e-05, "loss": 0.35932299494743347, "step": 302 }, { "epoch": 0.13196864111498258, "grad_norm": 3.01568865776062, "learning_rate": 5.874906660557845e-05, "loss": 0.30334898829460144, "step": 303 }, { "epoch": 0.13240418118466898, "grad_norm": 3.2705347537994385, "learning_rate": 5.87380503494406e-05, "loss": 0.33966773748397827, "step": 304 }, { "epoch": 0.1328397212543554, "grad_norm": 2.8459813594818115, "learning_rate": 5.872698684079973e-05, "loss": 0.31088122725486755, "step": 305 }, { "epoch": 0.1332752613240418, "grad_norm": 2.8871638774871826, "learning_rate": 5.8715876097847016e-05, "loss": 0.39034247398376465, "step": 306 }, { "epoch": 0.13371080139372823, "grad_norm": 4.1663994789123535, "learning_rate": 5.870471813885126e-05, "loss": 0.6248642206192017, "step": 307 }, { "epoch": 0.13414634146341464, "grad_norm": 4.300301551818848, "learning_rate": 5.869351298215895e-05, "loss": 0.7800649404525757, "step": 308 }, { "epoch": 0.13458188153310105, "grad_norm": 3.260450839996338, "learning_rate": 5.868226064619412e-05, "loss": 0.2849424183368683, "step": 309 }, { "epoch": 0.13501742160278746, "grad_norm": 3.0514910221099854, "learning_rate": 5.8670961149458436e-05, "loss": 0.3328036665916443, "step": 310 }, { "epoch": 0.13545296167247386, "grad_norm": 3.9534335136413574, "learning_rate": 5.865961451053107e-05, "loss": 0.6528239846229553, "step": 311 }, { "epoch": 0.13588850174216027, "grad_norm": 4.142487049102783, "learning_rate": 5.8648220748068714e-05, "loss": 0.5896745920181274, "step": 312 }, { "epoch": 0.13632404181184668, "grad_norm": 2.6488277912139893, "learning_rate": 5.863677988080555e-05, "loss": 0.15598152577877045, "step": 313 }, { "epoch": 0.1367595818815331, "grad_norm": 3.2811038494110107, "learning_rate": 5.8625291927553225e-05, "loss": 0.3515435457229614, "step": 314 }, { "epoch": 0.13719512195121952, "grad_norm": 3.985107898712158, "learning_rate": 5.8613756907200765e-05, "loss": 0.4326629042625427, "step": 315 }, { "epoch": 0.13763066202090593, "grad_norm": 3.6167123317718506, "learning_rate": 5.860217483871463e-05, "loss": 0.37209489941596985, "step": 316 }, { "epoch": 0.13806620209059234, "grad_norm": 3.6874396800994873, "learning_rate": 5.859054574113862e-05, "loss": 0.21563073992729187, "step": 317 }, { "epoch": 0.13850174216027875, "grad_norm": 4.237402439117432, "learning_rate": 5.8578869633593856e-05, "loss": 0.48311465978622437, "step": 318 }, { "epoch": 0.13893728222996515, "grad_norm": 2.9363856315612793, "learning_rate": 5.856714653527877e-05, "loss": 0.32102543115615845, "step": 319 }, { "epoch": 0.13937282229965156, "grad_norm": 2.245986223220825, "learning_rate": 5.855537646546906e-05, "loss": 0.17108489573001862, "step": 320 }, { "epoch": 0.13980836236933797, "grad_norm": 2.893437147140503, "learning_rate": 5.8543559443517626e-05, "loss": 0.37245070934295654, "step": 321 }, { "epoch": 0.1402439024390244, "grad_norm": 3.0935897827148438, "learning_rate": 5.853169548885461e-05, "loss": 0.5019145011901855, "step": 322 }, { "epoch": 0.1406794425087108, "grad_norm": 5.870626449584961, "learning_rate": 5.85197846209873e-05, "loss": 0.5496518015861511, "step": 323 }, { "epoch": 0.14111498257839722, "grad_norm": 3.308720588684082, "learning_rate": 5.850782685950012e-05, "loss": 0.3894205689430237, "step": 324 }, { "epoch": 0.14155052264808363, "grad_norm": 3.3871140480041504, "learning_rate": 5.849582222405461e-05, "loss": 0.3189050257205963, "step": 325 }, { "epoch": 0.14198606271777003, "grad_norm": 2.6264402866363525, "learning_rate": 5.848377073438938e-05, "loss": 0.2555387318134308, "step": 326 }, { "epoch": 0.14242160278745644, "grad_norm": 3.5241360664367676, "learning_rate": 5.847167241032006e-05, "loss": 0.5328623652458191, "step": 327 }, { "epoch": 0.14285714285714285, "grad_norm": 10.405203819274902, "learning_rate": 5.845952727173933e-05, "loss": 0.37476304173469543, "step": 328 }, { "epoch": 0.14329268292682926, "grad_norm": 2.7880072593688965, "learning_rate": 5.844733533861679e-05, "loss": 0.2289225310087204, "step": 329 }, { "epoch": 0.1437282229965157, "grad_norm": 2.890775203704834, "learning_rate": 5.843509663099904e-05, "loss": 0.3335177004337311, "step": 330 }, { "epoch": 0.1441637630662021, "grad_norm": 3.10864520072937, "learning_rate": 5.842281116900953e-05, "loss": 0.36614590883255005, "step": 331 }, { "epoch": 0.1445993031358885, "grad_norm": 2.7503323554992676, "learning_rate": 5.841047897284864e-05, "loss": 0.2282811552286148, "step": 332 }, { "epoch": 0.14503484320557491, "grad_norm": 3.9090466499328613, "learning_rate": 5.839810006279355e-05, "loss": 0.5526589751243591, "step": 333 }, { "epoch": 0.14547038327526132, "grad_norm": 2.721558094024658, "learning_rate": 5.8385674459198293e-05, "loss": 0.1679580807685852, "step": 334 }, { "epoch": 0.14590592334494773, "grad_norm": 4.967030048370361, "learning_rate": 5.837320218249361e-05, "loss": 0.5397082567214966, "step": 335 }, { "epoch": 0.14634146341463414, "grad_norm": 2.8730831146240234, "learning_rate": 5.8360683253187064e-05, "loss": 0.49895915389060974, "step": 336 }, { "epoch": 0.14677700348432055, "grad_norm": 3.6818113327026367, "learning_rate": 5.834811769186288e-05, "loss": 0.4961114525794983, "step": 337 }, { "epoch": 0.14721254355400698, "grad_norm": 3.3775928020477295, "learning_rate": 5.833550551918196e-05, "loss": 0.5750399827957153, "step": 338 }, { "epoch": 0.1476480836236934, "grad_norm": 2.630991220474243, "learning_rate": 5.8322846755881844e-05, "loss": 0.17237579822540283, "step": 339 }, { "epoch": 0.1480836236933798, "grad_norm": 2.1829628944396973, "learning_rate": 5.8310141422776704e-05, "loss": 0.2518506944179535, "step": 340 }, { "epoch": 0.1485191637630662, "grad_norm": 3.1226797103881836, "learning_rate": 5.8297389540757264e-05, "loss": 0.5372876524925232, "step": 341 }, { "epoch": 0.1489547038327526, "grad_norm": 3.109635591506958, "learning_rate": 5.828459113079079e-05, "loss": 0.23638257384300232, "step": 342 }, { "epoch": 0.14939024390243902, "grad_norm": 2.893676519393921, "learning_rate": 5.827174621392105e-05, "loss": 0.3341526985168457, "step": 343 }, { "epoch": 0.14982578397212543, "grad_norm": 3.0126700401306152, "learning_rate": 5.825885481126827e-05, "loss": 0.30167242884635925, "step": 344 }, { "epoch": 0.15026132404181183, "grad_norm": 3.7824339866638184, "learning_rate": 5.8245916944029144e-05, "loss": 0.5100857019424438, "step": 345 }, { "epoch": 0.15069686411149827, "grad_norm": 3.7733497619628906, "learning_rate": 5.8232932633476734e-05, "loss": 0.5847695469856262, "step": 346 }, { "epoch": 0.15113240418118468, "grad_norm": 2.5057897567749023, "learning_rate": 5.8219901900960476e-05, "loss": 0.20945973694324493, "step": 347 }, { "epoch": 0.15156794425087108, "grad_norm": 2.862794876098633, "learning_rate": 5.820682476790614e-05, "loss": 0.26181623339653015, "step": 348 }, { "epoch": 0.1520034843205575, "grad_norm": 3.6921818256378174, "learning_rate": 5.819370125581577e-05, "loss": 0.6429627537727356, "step": 349 }, { "epoch": 0.1524390243902439, "grad_norm": 3.4509518146514893, "learning_rate": 5.818053138626771e-05, "loss": 0.4285081624984741, "step": 350 }, { "epoch": 0.1528745644599303, "grad_norm": 2.1838231086730957, "learning_rate": 5.8167315180916475e-05, "loss": 0.23856952786445618, "step": 351 }, { "epoch": 0.15331010452961671, "grad_norm": 4.499940872192383, "learning_rate": 5.8154052661492814e-05, "loss": 0.6542803049087524, "step": 352 }, { "epoch": 0.15374564459930315, "grad_norm": 2.9323813915252686, "learning_rate": 5.81407438498036e-05, "loss": 0.3660646378993988, "step": 353 }, { "epoch": 0.15418118466898956, "grad_norm": 2.4150519371032715, "learning_rate": 5.812738876773182e-05, "loss": 0.1559220552444458, "step": 354 }, { "epoch": 0.15461672473867596, "grad_norm": 4.202732086181641, "learning_rate": 5.811398743723657e-05, "loss": 0.4209378957748413, "step": 355 }, { "epoch": 0.15505226480836237, "grad_norm": 2.4548439979553223, "learning_rate": 5.8100539880352964e-05, "loss": 0.22386117279529572, "step": 356 }, { "epoch": 0.15548780487804878, "grad_norm": 3.3079488277435303, "learning_rate": 5.808704611919212e-05, "loss": 0.46925926208496094, "step": 357 }, { "epoch": 0.1559233449477352, "grad_norm": 3.3249030113220215, "learning_rate": 5.807350617594114e-05, "loss": 0.2813144028186798, "step": 358 }, { "epoch": 0.1563588850174216, "grad_norm": 2.5232508182525635, "learning_rate": 5.805992007286308e-05, "loss": 0.3266029357910156, "step": 359 }, { "epoch": 0.156794425087108, "grad_norm": 3.212397813796997, "learning_rate": 5.804628783229685e-05, "loss": 0.43195345997810364, "step": 360 }, { "epoch": 0.15722996515679444, "grad_norm": 3.1499733924865723, "learning_rate": 5.803260947665725e-05, "loss": 0.3817780613899231, "step": 361 }, { "epoch": 0.15766550522648085, "grad_norm": 3.6318905353546143, "learning_rate": 5.8018885028434896e-05, "loss": 0.299665242433548, "step": 362 }, { "epoch": 0.15810104529616725, "grad_norm": 3.650736093521118, "learning_rate": 5.8005114510196204e-05, "loss": 0.27266037464141846, "step": 363 }, { "epoch": 0.15853658536585366, "grad_norm": 2.3392574787139893, "learning_rate": 5.7991297944583326e-05, "loss": 0.294393390417099, "step": 364 }, { "epoch": 0.15897212543554007, "grad_norm": 2.7203664779663086, "learning_rate": 5.797743535431414e-05, "loss": 0.20500853657722473, "step": 365 }, { "epoch": 0.15940766550522648, "grad_norm": 3.0068352222442627, "learning_rate": 5.796352676218217e-05, "loss": 0.4201393127441406, "step": 366 }, { "epoch": 0.15984320557491288, "grad_norm": 4.926451683044434, "learning_rate": 5.7949572191056625e-05, "loss": 0.5963433980941772, "step": 367 }, { "epoch": 0.1602787456445993, "grad_norm": 3.0790085792541504, "learning_rate": 5.793557166388228e-05, "loss": 0.34307345747947693, "step": 368 }, { "epoch": 0.16071428571428573, "grad_norm": 3.2974956035614014, "learning_rate": 5.7921525203679493e-05, "loss": 0.40867480635643005, "step": 369 }, { "epoch": 0.16114982578397213, "grad_norm": 3.0908453464508057, "learning_rate": 5.7907432833544125e-05, "loss": 0.39343345165252686, "step": 370 }, { "epoch": 0.16158536585365854, "grad_norm": 3.0946133136749268, "learning_rate": 5.789329457664754e-05, "loss": 0.4469483196735382, "step": 371 }, { "epoch": 0.16202090592334495, "grad_norm": 3.3782730102539062, "learning_rate": 5.787911045623656e-05, "loss": 0.3448239266872406, "step": 372 }, { "epoch": 0.16245644599303136, "grad_norm": 3.3905892372131348, "learning_rate": 5.78648804956334e-05, "loss": 0.49512943625450134, "step": 373 }, { "epoch": 0.16289198606271776, "grad_norm": 3.835350513458252, "learning_rate": 5.785060471823566e-05, "loss": 0.37304946780204773, "step": 374 }, { "epoch": 0.16332752613240417, "grad_norm": 4.430235385894775, "learning_rate": 5.783628314751626e-05, "loss": 0.3764013350009918, "step": 375 }, { "epoch": 0.16376306620209058, "grad_norm": 3.1338720321655273, "learning_rate": 5.782191580702344e-05, "loss": 0.3681105673313141, "step": 376 }, { "epoch": 0.16419860627177701, "grad_norm": 4.322766304016113, "learning_rate": 5.7807502720380655e-05, "loss": 0.5008698105812073, "step": 377 }, { "epoch": 0.16463414634146342, "grad_norm": 3.038327932357788, "learning_rate": 5.779304391128662e-05, "loss": 0.39290112257003784, "step": 378 }, { "epoch": 0.16506968641114983, "grad_norm": 3.0575621128082275, "learning_rate": 5.777853940351523e-05, "loss": 0.22081999480724335, "step": 379 }, { "epoch": 0.16550522648083624, "grad_norm": 6.143305778503418, "learning_rate": 5.776398922091548e-05, "loss": 0.5169167518615723, "step": 380 }, { "epoch": 0.16594076655052264, "grad_norm": 2.3610904216766357, "learning_rate": 5.774939338741149e-05, "loss": 0.1692521572113037, "step": 381 }, { "epoch": 0.16637630662020905, "grad_norm": 2.9524288177490234, "learning_rate": 5.773475192700245e-05, "loss": 0.2333371490240097, "step": 382 }, { "epoch": 0.16681184668989546, "grad_norm": 2.895930767059326, "learning_rate": 5.772006486376256e-05, "loss": 0.5078673958778381, "step": 383 }, { "epoch": 0.1672473867595819, "grad_norm": 2.327312707901001, "learning_rate": 5.7705332221841004e-05, "loss": 0.29399269819259644, "step": 384 }, { "epoch": 0.1676829268292683, "grad_norm": 3.972898483276367, "learning_rate": 5.7690554025461926e-05, "loss": 0.5167810916900635, "step": 385 }, { "epoch": 0.1681184668989547, "grad_norm": 3.638333797454834, "learning_rate": 5.767573029892433e-05, "loss": 0.6212786436080933, "step": 386 }, { "epoch": 0.16855400696864112, "grad_norm": 2.6218979358673096, "learning_rate": 5.766086106660212e-05, "loss": 0.36016392707824707, "step": 387 }, { "epoch": 0.16898954703832753, "grad_norm": 3.568425416946411, "learning_rate": 5.764594635294401e-05, "loss": 0.38378381729125977, "step": 388 }, { "epoch": 0.16942508710801393, "grad_norm": 2.461933135986328, "learning_rate": 5.763098618247352e-05, "loss": 0.2846580445766449, "step": 389 }, { "epoch": 0.16986062717770034, "grad_norm": 3.510734796524048, "learning_rate": 5.7615980579788866e-05, "loss": 0.5628392100334167, "step": 390 }, { "epoch": 0.17029616724738675, "grad_norm": 4.032413005828857, "learning_rate": 5.760092956956299e-05, "loss": 0.3166201710700989, "step": 391 }, { "epoch": 0.17073170731707318, "grad_norm": 5.332808494567871, "learning_rate": 5.7585833176543523e-05, "loss": 0.39749202132225037, "step": 392 }, { "epoch": 0.1711672473867596, "grad_norm": 2.7166059017181396, "learning_rate": 5.757069142555267e-05, "loss": 0.2836206257343292, "step": 393 }, { "epoch": 0.171602787456446, "grad_norm": 2.8603949546813965, "learning_rate": 5.7555504341487234e-05, "loss": 0.3909367024898529, "step": 394 }, { "epoch": 0.1720383275261324, "grad_norm": 3.053326368331909, "learning_rate": 5.754027194931856e-05, "loss": 0.5241299867630005, "step": 395 }, { "epoch": 0.17247386759581881, "grad_norm": 3.1499178409576416, "learning_rate": 5.752499427409251e-05, "loss": 0.602374255657196, "step": 396 }, { "epoch": 0.17290940766550522, "grad_norm": 3.6846296787261963, "learning_rate": 5.7509671340929355e-05, "loss": 0.35683053731918335, "step": 397 }, { "epoch": 0.17334494773519163, "grad_norm": 2.823683738708496, "learning_rate": 5.7494303175023825e-05, "loss": 0.26556044816970825, "step": 398 }, { "epoch": 0.17378048780487804, "grad_norm": 3.7188608646392822, "learning_rate": 5.7478889801645e-05, "loss": 0.5656572580337524, "step": 399 }, { "epoch": 0.17421602787456447, "grad_norm": 3.4140899181365967, "learning_rate": 5.74634312461363e-05, "loss": 0.4407804310321808, "step": 400 }, { "epoch": 0.17465156794425088, "grad_norm": 2.633164167404175, "learning_rate": 5.7447927533915444e-05, "loss": 0.259867399930954, "step": 401 }, { "epoch": 0.1750871080139373, "grad_norm": 3.6294641494750977, "learning_rate": 5.743237869047438e-05, "loss": 0.7187398076057434, "step": 402 }, { "epoch": 0.1755226480836237, "grad_norm": 3.009660243988037, "learning_rate": 5.7416784741379274e-05, "loss": 0.4730783998966217, "step": 403 }, { "epoch": 0.1759581881533101, "grad_norm": 2.3565995693206787, "learning_rate": 5.7401145712270464e-05, "loss": 0.17444337904453278, "step": 404 }, { "epoch": 0.1763937282229965, "grad_norm": 2.3016297817230225, "learning_rate": 5.738546162886241e-05, "loss": 0.24557653069496155, "step": 405 }, { "epoch": 0.17682926829268292, "grad_norm": 4.1529717445373535, "learning_rate": 5.736973251694363e-05, "loss": 0.23661747574806213, "step": 406 }, { "epoch": 0.17726480836236932, "grad_norm": 3.7318098545074463, "learning_rate": 5.7353958402376705e-05, "loss": 0.3016824424266815, "step": 407 }, { "epoch": 0.17770034843205576, "grad_norm": 2.309924840927124, "learning_rate": 5.733813931109821e-05, "loss": 0.16430430114269257, "step": 408 }, { "epoch": 0.17813588850174217, "grad_norm": 2.177198886871338, "learning_rate": 5.7322275269118654e-05, "loss": 0.17235147953033447, "step": 409 }, { "epoch": 0.17857142857142858, "grad_norm": 2.956559658050537, "learning_rate": 5.730636630252247e-05, "loss": 0.4217454493045807, "step": 410 }, { "epoch": 0.17900696864111498, "grad_norm": 2.0801639556884766, "learning_rate": 5.729041243746796e-05, "loss": 0.2157486230134964, "step": 411 }, { "epoch": 0.1794425087108014, "grad_norm": 6.07927131652832, "learning_rate": 5.727441370018725e-05, "loss": 0.5806931853294373, "step": 412 }, { "epoch": 0.1798780487804878, "grad_norm": 2.6141040325164795, "learning_rate": 5.725837011698623e-05, "loss": 0.33312302827835083, "step": 413 }, { "epoch": 0.1803135888501742, "grad_norm": 2.9973456859588623, "learning_rate": 5.7242281714244555e-05, "loss": 0.41377151012420654, "step": 414 }, { "epoch": 0.18074912891986064, "grad_norm": 2.15769100189209, "learning_rate": 5.722614851841557e-05, "loss": 0.1909504383802414, "step": 415 }, { "epoch": 0.18118466898954705, "grad_norm": 3.482913017272949, "learning_rate": 5.720997055602622e-05, "loss": 0.49475884437561035, "step": 416 }, { "epoch": 0.18162020905923346, "grad_norm": 2.951566696166992, "learning_rate": 5.7193747853677144e-05, "loss": 0.5117514133453369, "step": 417 }, { "epoch": 0.18205574912891986, "grad_norm": 2.646484375, "learning_rate": 5.7177480438042484e-05, "loss": 0.27676504850387573, "step": 418 }, { "epoch": 0.18249128919860627, "grad_norm": 2.9160587787628174, "learning_rate": 5.716116833586991e-05, "loss": 0.423473984003067, "step": 419 }, { "epoch": 0.18292682926829268, "grad_norm": 2.7105772495269775, "learning_rate": 5.7144811573980586e-05, "loss": 0.24852384626865387, "step": 420 }, { "epoch": 0.1833623693379791, "grad_norm": 3.320552110671997, "learning_rate": 5.7128410179269096e-05, "loss": 0.41279682517051697, "step": 421 }, { "epoch": 0.1837979094076655, "grad_norm": 4.013285160064697, "learning_rate": 5.7111964178703406e-05, "loss": 0.21642212569713593, "step": 422 }, { "epoch": 0.18423344947735193, "grad_norm": 2.4734084606170654, "learning_rate": 5.709547359932483e-05, "loss": 0.30680298805236816, "step": 423 }, { "epoch": 0.18466898954703834, "grad_norm": 2.6160335540771484, "learning_rate": 5.7078938468247996e-05, "loss": 0.28854677081108093, "step": 424 }, { "epoch": 0.18510452961672474, "grad_norm": 11.225839614868164, "learning_rate": 5.706235881266076e-05, "loss": 0.8473872542381287, "step": 425 }, { "epoch": 0.18554006968641115, "grad_norm": 4.983267784118652, "learning_rate": 5.704573465982421e-05, "loss": 0.40326401591300964, "step": 426 }, { "epoch": 0.18597560975609756, "grad_norm": 3.467745304107666, "learning_rate": 5.702906603707257e-05, "loss": 0.45423075556755066, "step": 427 }, { "epoch": 0.18641114982578397, "grad_norm": 4.141380310058594, "learning_rate": 5.701235297181323e-05, "loss": 0.4765985310077667, "step": 428 }, { "epoch": 0.18684668989547037, "grad_norm": 2.7531843185424805, "learning_rate": 5.69955954915266e-05, "loss": 0.21389271318912506, "step": 429 }, { "epoch": 0.18728222996515678, "grad_norm": 2.7568931579589844, "learning_rate": 5.697879362376616e-05, "loss": 0.44873806834220886, "step": 430 }, { "epoch": 0.18771777003484322, "grad_norm": 3.4245147705078125, "learning_rate": 5.6961947396158356e-05, "loss": 0.5183812379837036, "step": 431 }, { "epoch": 0.18815331010452963, "grad_norm": 2.7614827156066895, "learning_rate": 5.6945056836402566e-05, "loss": 0.23446352779865265, "step": 432 }, { "epoch": 0.18858885017421603, "grad_norm": 2.4439728260040283, "learning_rate": 5.6928121972271104e-05, "loss": 0.2790519595146179, "step": 433 }, { "epoch": 0.18902439024390244, "grad_norm": 3.062150478363037, "learning_rate": 5.691114283160906e-05, "loss": 0.667241096496582, "step": 434 }, { "epoch": 0.18945993031358885, "grad_norm": 6.293123722076416, "learning_rate": 5.689411944233439e-05, "loss": 0.35569697618484497, "step": 435 }, { "epoch": 0.18989547038327526, "grad_norm": 2.586483955383301, "learning_rate": 5.687705183243777e-05, "loss": 0.3412120044231415, "step": 436 }, { "epoch": 0.19033101045296166, "grad_norm": 3.4411263465881348, "learning_rate": 5.68599400299826e-05, "loss": 0.4637414216995239, "step": 437 }, { "epoch": 0.19076655052264807, "grad_norm": 3.214369773864746, "learning_rate": 5.684278406310493e-05, "loss": 0.43616122007369995, "step": 438 }, { "epoch": 0.1912020905923345, "grad_norm": 4.95930814743042, "learning_rate": 5.682558396001345e-05, "loss": 0.5177434086799622, "step": 439 }, { "epoch": 0.1916376306620209, "grad_norm": 2.650282382965088, "learning_rate": 5.68083397489894e-05, "loss": 0.4715700149536133, "step": 440 }, { "epoch": 0.19207317073170732, "grad_norm": 2.928900718688965, "learning_rate": 5.679105145838657e-05, "loss": 0.2337208390235901, "step": 441 }, { "epoch": 0.19250871080139373, "grad_norm": 3.052281379699707, "learning_rate": 5.677371911663118e-05, "loss": 0.5388917326927185, "step": 442 }, { "epoch": 0.19294425087108014, "grad_norm": 2.7061450481414795, "learning_rate": 5.6756342752221926e-05, "loss": 0.44527140259742737, "step": 443 }, { "epoch": 0.19337979094076654, "grad_norm": 2.047010660171509, "learning_rate": 5.6738922393729876e-05, "loss": 0.25706106424331665, "step": 444 }, { "epoch": 0.19381533101045295, "grad_norm": 5.4084272384643555, "learning_rate": 5.672145806979842e-05, "loss": 0.693732500076294, "step": 445 }, { "epoch": 0.19425087108013936, "grad_norm": 3.09945011138916, "learning_rate": 5.670394980914328e-05, "loss": 0.315384179353714, "step": 446 }, { "epoch": 0.1946864111498258, "grad_norm": 2.6355202198028564, "learning_rate": 5.668639764055236e-05, "loss": 0.45389968156814575, "step": 447 }, { "epoch": 0.1951219512195122, "grad_norm": 2.0075201988220215, "learning_rate": 5.66688015928858e-05, "loss": 0.18614061176776886, "step": 448 }, { "epoch": 0.1955574912891986, "grad_norm": 2.3727307319641113, "learning_rate": 5.6651161695075884e-05, "loss": 0.16602136194705963, "step": 449 }, { "epoch": 0.19599303135888502, "grad_norm": 3.731719970703125, "learning_rate": 5.663347797612699e-05, "loss": 0.33041632175445557, "step": 450 }, { "epoch": 0.19642857142857142, "grad_norm": 2.605224847793579, "learning_rate": 5.6615750465115553e-05, "loss": 0.4029352068901062, "step": 451 }, { "epoch": 0.19686411149825783, "grad_norm": 2.325559616088867, "learning_rate": 5.6597979191190005e-05, "loss": 0.2628800570964813, "step": 452 }, { "epoch": 0.19729965156794424, "grad_norm": 1.946218729019165, "learning_rate": 5.658016418357074e-05, "loss": 0.15498803555965424, "step": 453 }, { "epoch": 0.19773519163763068, "grad_norm": 248.51025390625, "learning_rate": 5.656230547155008e-05, "loss": 3.988314390182495, "step": 454 }, { "epoch": 0.19817073170731708, "grad_norm": 3.5869944095611572, "learning_rate": 5.6544403084492155e-05, "loss": 0.45759788155555725, "step": 455 }, { "epoch": 0.1986062717770035, "grad_norm": 5.973674297332764, "learning_rate": 5.652645705183297e-05, "loss": 0.44340991973876953, "step": 456 }, { "epoch": 0.1990418118466899, "grad_norm": 3.0261120796203613, "learning_rate": 5.650846740308026e-05, "loss": 0.46621379256248474, "step": 457 }, { "epoch": 0.1994773519163763, "grad_norm": 2.5985636711120605, "learning_rate": 5.649043416781347e-05, "loss": 0.37670281529426575, "step": 458 }, { "epoch": 0.1999128919860627, "grad_norm": 4.255541801452637, "learning_rate": 5.647235737568376e-05, "loss": 0.3623659014701843, "step": 459 }, { "epoch": 0.20034843205574912, "grad_norm": 3.634413003921509, "learning_rate": 5.645423705641383e-05, "loss": 0.2825435400009155, "step": 460 }, { "epoch": 0.20078397212543553, "grad_norm": 3.1250483989715576, "learning_rate": 5.6436073239798015e-05, "loss": 0.3223016858100891, "step": 461 }, { "epoch": 0.20121951219512196, "grad_norm": 2.211331844329834, "learning_rate": 5.641786595570214e-05, "loss": 0.39748725295066833, "step": 462 }, { "epoch": 0.20165505226480837, "grad_norm": 2.9066059589385986, "learning_rate": 5.639961523406351e-05, "loss": 0.5434019565582275, "step": 463 }, { "epoch": 0.20209059233449478, "grad_norm": 2.308541774749756, "learning_rate": 5.638132110489086e-05, "loss": 0.2683337926864624, "step": 464 }, { "epoch": 0.20252613240418119, "grad_norm": 3.197903871536255, "learning_rate": 5.636298359826428e-05, "loss": 0.5274491906166077, "step": 465 }, { "epoch": 0.2029616724738676, "grad_norm": 2.0946524143218994, "learning_rate": 5.6344602744335184e-05, "loss": 0.24602563679218292, "step": 466 }, { "epoch": 0.203397212543554, "grad_norm": 4.435793399810791, "learning_rate": 5.6326178573326295e-05, "loss": 0.45035260915756226, "step": 467 }, { "epoch": 0.2038327526132404, "grad_norm": 2.7595176696777344, "learning_rate": 5.63077111155315e-05, "loss": 0.35273417830467224, "step": 468 }, { "epoch": 0.20426829268292682, "grad_norm": 2.701477527618408, "learning_rate": 5.6289200401315906e-05, "loss": 0.40391775965690613, "step": 469 }, { "epoch": 0.20470383275261325, "grad_norm": 2.315180778503418, "learning_rate": 5.6270646461115747e-05, "loss": 0.22713856399059296, "step": 470 }, { "epoch": 0.20513937282229966, "grad_norm": 2.58843994140625, "learning_rate": 5.6252049325438295e-05, "loss": 0.45999160408973694, "step": 471 }, { "epoch": 0.20557491289198607, "grad_norm": 59.73284912109375, "learning_rate": 5.623340902486187e-05, "loss": 1.4801427125930786, "step": 472 }, { "epoch": 0.20601045296167247, "grad_norm": 2.2025094032287598, "learning_rate": 5.621472559003578e-05, "loss": 0.2753940522670746, "step": 473 }, { "epoch": 0.20644599303135888, "grad_norm": 6.605295658111572, "learning_rate": 5.619599905168021e-05, "loss": 0.43076926469802856, "step": 474 }, { "epoch": 0.2068815331010453, "grad_norm": 3.9197635650634766, "learning_rate": 5.617722944058628e-05, "loss": 0.555379331111908, "step": 475 }, { "epoch": 0.2073170731707317, "grad_norm": 3.0363945960998535, "learning_rate": 5.6158416787615874e-05, "loss": 0.28737494349479675, "step": 476 }, { "epoch": 0.2077526132404181, "grad_norm": 3.191235303878784, "learning_rate": 5.613956112370168e-05, "loss": 0.6662890315055847, "step": 477 }, { "epoch": 0.20818815331010454, "grad_norm": 2.4153549671173096, "learning_rate": 5.61206624798471e-05, "loss": 0.37223950028419495, "step": 478 }, { "epoch": 0.20862369337979095, "grad_norm": 2.5620276927948, "learning_rate": 5.6101720887126215e-05, "loss": 0.13547761738300323, "step": 479 }, { "epoch": 0.20905923344947736, "grad_norm": 3.0297389030456543, "learning_rate": 5.6082736376683706e-05, "loss": 0.3918512761592865, "step": 480 }, { "epoch": 0.20949477351916376, "grad_norm": 2.991147994995117, "learning_rate": 5.6063708979734826e-05, "loss": 0.43971002101898193, "step": 481 }, { "epoch": 0.20993031358885017, "grad_norm": 2.4670262336730957, "learning_rate": 5.604463872756535e-05, "loss": 0.25469866394996643, "step": 482 }, { "epoch": 0.21036585365853658, "grad_norm": 3.0097854137420654, "learning_rate": 5.6025525651531525e-05, "loss": 0.4463574290275574, "step": 483 }, { "epoch": 0.21080139372822299, "grad_norm": 3.6692404747009277, "learning_rate": 5.600636978306e-05, "loss": 0.6650458574295044, "step": 484 }, { "epoch": 0.21123693379790942, "grad_norm": 2.676802635192871, "learning_rate": 5.598717115364778e-05, "loss": 0.2255852371454239, "step": 485 }, { "epoch": 0.21167247386759583, "grad_norm": 1.793445110321045, "learning_rate": 5.5967929794862185e-05, "loss": 0.19365793466567993, "step": 486 }, { "epoch": 0.21210801393728224, "grad_norm": 3.4050021171569824, "learning_rate": 5.594864573834081e-05, "loss": 0.5663712024688721, "step": 487 }, { "epoch": 0.21254355400696864, "grad_norm": 5.212076663970947, "learning_rate": 5.5929319015791424e-05, "loss": 0.5150182843208313, "step": 488 }, { "epoch": 0.21297909407665505, "grad_norm": 1.9778928756713867, "learning_rate": 5.5909949658991984e-05, "loss": 0.0955156460404396, "step": 489 }, { "epoch": 0.21341463414634146, "grad_norm": 2.2691402435302734, "learning_rate": 5.5890537699790504e-05, "loss": 0.34243911504745483, "step": 490 }, { "epoch": 0.21385017421602787, "grad_norm": 3.0053064823150635, "learning_rate": 5.587108317010511e-05, "loss": 0.23516543209552765, "step": 491 }, { "epoch": 0.21428571428571427, "grad_norm": 2.569539785385132, "learning_rate": 5.5851586101923855e-05, "loss": 0.40535518527030945, "step": 492 }, { "epoch": 0.2147212543554007, "grad_norm": 1.8088382482528687, "learning_rate": 5.583204652730478e-05, "loss": 0.19923770427703857, "step": 493 }, { "epoch": 0.21515679442508712, "grad_norm": 3.086596965789795, "learning_rate": 5.581246447837581e-05, "loss": 0.3753933310508728, "step": 494 }, { "epoch": 0.21559233449477352, "grad_norm": 2.307676315307617, "learning_rate": 5.57928399873347e-05, "loss": 0.23381267488002777, "step": 495 }, { "epoch": 0.21602787456445993, "grad_norm": 2.9633724689483643, "learning_rate": 5.5773173086449005e-05, "loss": 0.2984374463558197, "step": 496 }, { "epoch": 0.21646341463414634, "grad_norm": 2.1099798679351807, "learning_rate": 5.575346380805599e-05, "loss": 0.24412637948989868, "step": 497 }, { "epoch": 0.21689895470383275, "grad_norm": 2.467271089553833, "learning_rate": 5.57337121845626e-05, "loss": 0.1961180418729782, "step": 498 }, { "epoch": 0.21733449477351915, "grad_norm": 2.884908676147461, "learning_rate": 5.571391824844545e-05, "loss": 0.5709798336029053, "step": 499 }, { "epoch": 0.21777003484320556, "grad_norm": 2.5026917457580566, "learning_rate": 5.569408203225067e-05, "loss": 0.38770389556884766, "step": 500 }, { "epoch": 0.218205574912892, "grad_norm": 1.9116250276565552, "learning_rate": 5.567420356859393e-05, "loss": 0.10600558668375015, "step": 501 }, { "epoch": 0.2186411149825784, "grad_norm": 2.14990496635437, "learning_rate": 5.565428289016039e-05, "loss": 0.22628635168075562, "step": 502 }, { "epoch": 0.2190766550522648, "grad_norm": 3.923018217086792, "learning_rate": 5.5634320029704576e-05, "loss": 0.522826075553894, "step": 503 }, { "epoch": 0.21951219512195122, "grad_norm": 3.0573270320892334, "learning_rate": 5.5614315020050417e-05, "loss": 0.45696744322776794, "step": 504 }, { "epoch": 0.21994773519163763, "grad_norm": 2.963902235031128, "learning_rate": 5.559426789409112e-05, "loss": 0.32126572728157043, "step": 505 }, { "epoch": 0.22038327526132404, "grad_norm": 3.53619122505188, "learning_rate": 5.557417868478913e-05, "loss": 0.34392979741096497, "step": 506 }, { "epoch": 0.22081881533101044, "grad_norm": 3.254573106765747, "learning_rate": 5.555404742517613e-05, "loss": 0.5475251078605652, "step": 507 }, { "epoch": 0.22125435540069685, "grad_norm": 1.9974862337112427, "learning_rate": 5.55338741483529e-05, "loss": 0.16820408403873444, "step": 508 }, { "epoch": 0.22168989547038329, "grad_norm": 2.0044822692871094, "learning_rate": 5.551365888748932e-05, "loss": 0.18580523133277893, "step": 509 }, { "epoch": 0.2221254355400697, "grad_norm": 3.0676891803741455, "learning_rate": 5.5493401675824335e-05, "loss": 0.3569593131542206, "step": 510 }, { "epoch": 0.2225609756097561, "grad_norm": 1.8743780851364136, "learning_rate": 5.5473102546665816e-05, "loss": 0.19013668596744537, "step": 511 }, { "epoch": 0.2229965156794425, "grad_norm": 3.1050829887390137, "learning_rate": 5.545276153339058e-05, "loss": 0.3429447114467621, "step": 512 }, { "epoch": 0.22343205574912892, "grad_norm": 2.7670722007751465, "learning_rate": 5.543237866944432e-05, "loss": 0.22625048458576202, "step": 513 }, { "epoch": 0.22386759581881532, "grad_norm": 2.255389928817749, "learning_rate": 5.541195398834153e-05, "loss": 0.11060892790555954, "step": 514 }, { "epoch": 0.22430313588850173, "grad_norm": 3.2096235752105713, "learning_rate": 5.539148752366547e-05, "loss": 0.4126913845539093, "step": 515 }, { "epoch": 0.22473867595818817, "grad_norm": 3.147122621536255, "learning_rate": 5.537097930906811e-05, "loss": 0.43897491693496704, "step": 516 }, { "epoch": 0.22517421602787457, "grad_norm": 4.295405864715576, "learning_rate": 5.535042937827004e-05, "loss": 0.4825495779514313, "step": 517 }, { "epoch": 0.22560975609756098, "grad_norm": 8.302755355834961, "learning_rate": 5.5329837765060454e-05, "loss": 0.48595091700553894, "step": 518 }, { "epoch": 0.2260452961672474, "grad_norm": 2.0586352348327637, "learning_rate": 5.5309204503297104e-05, "loss": 0.2588714361190796, "step": 519 }, { "epoch": 0.2264808362369338, "grad_norm": 3.6186585426330566, "learning_rate": 5.5288529626906184e-05, "loss": 0.5523048043251038, "step": 520 }, { "epoch": 0.2269163763066202, "grad_norm": 3.2036564350128174, "learning_rate": 5.5267813169882346e-05, "loss": 0.5375420451164246, "step": 521 }, { "epoch": 0.2273519163763066, "grad_norm": 1.9075562953948975, "learning_rate": 5.52470551662886e-05, "loss": 0.1914283186197281, "step": 522 }, { "epoch": 0.22778745644599302, "grad_norm": 1.9798812866210938, "learning_rate": 5.522625565025626e-05, "loss": 0.17384450137615204, "step": 523 }, { "epoch": 0.22822299651567945, "grad_norm": 2.6905782222747803, "learning_rate": 5.5205414655984907e-05, "loss": 0.4978514015674591, "step": 524 }, { "epoch": 0.22865853658536586, "grad_norm": 3.3779313564300537, "learning_rate": 5.5184532217742315e-05, "loss": 0.3461341857910156, "step": 525 }, { "epoch": 0.22909407665505227, "grad_norm": 2.1723992824554443, "learning_rate": 5.516360836986442e-05, "loss": 0.17703719437122345, "step": 526 }, { "epoch": 0.22952961672473868, "grad_norm": 1.9252556562423706, "learning_rate": 5.5142643146755215e-05, "loss": 0.24247752130031586, "step": 527 }, { "epoch": 0.22996515679442509, "grad_norm": 63.143653869628906, "learning_rate": 5.512163658288676e-05, "loss": 1.545414924621582, "step": 528 }, { "epoch": 0.2304006968641115, "grad_norm": 4.05615234375, "learning_rate": 5.510058871279906e-05, "loss": 0.15074379742145538, "step": 529 }, { "epoch": 0.2308362369337979, "grad_norm": 2.5352370738983154, "learning_rate": 5.507949957110005e-05, "loss": 0.26275303959846497, "step": 530 }, { "epoch": 0.2312717770034843, "grad_norm": 3.075396776199341, "learning_rate": 5.5058369192465526e-05, "loss": 0.39978256821632385, "step": 531 }, { "epoch": 0.23170731707317074, "grad_norm": 3.0044796466827393, "learning_rate": 5.5037197611639083e-05, "loss": 0.4790782034397125, "step": 532 }, { "epoch": 0.23214285714285715, "grad_norm": 3.606722354888916, "learning_rate": 5.5015984863432074e-05, "loss": 0.3166565001010895, "step": 533 }, { "epoch": 0.23257839721254356, "grad_norm": 3.0490329265594482, "learning_rate": 5.499473098272352e-05, "loss": 0.37955307960510254, "step": 534 }, { "epoch": 0.23301393728222997, "grad_norm": 3.1137914657592773, "learning_rate": 5.49734360044601e-05, "loss": 0.46020975708961487, "step": 535 }, { "epoch": 0.23344947735191637, "grad_norm": 2.517592191696167, "learning_rate": 5.4952099963656044e-05, "loss": 0.28713101148605347, "step": 536 }, { "epoch": 0.23388501742160278, "grad_norm": 2.476351261138916, "learning_rate": 5.493072289539312e-05, "loss": 0.3367736041545868, "step": 537 }, { "epoch": 0.2343205574912892, "grad_norm": 2.88899827003479, "learning_rate": 5.490930483482054e-05, "loss": 0.42216894030570984, "step": 538 }, { "epoch": 0.2347560975609756, "grad_norm": 2.648317337036133, "learning_rate": 5.488784581715494e-05, "loss": 0.3768916726112366, "step": 539 }, { "epoch": 0.23519163763066203, "grad_norm": 1.8454852104187012, "learning_rate": 5.4866345877680256e-05, "loss": 0.15335480868816376, "step": 540 }, { "epoch": 0.23562717770034844, "grad_norm": 3.2238688468933105, "learning_rate": 5.484480505174775e-05, "loss": 0.6146450638771057, "step": 541 }, { "epoch": 0.23606271777003485, "grad_norm": 2.4257168769836426, "learning_rate": 5.48232233747759e-05, "loss": 0.1650456190109253, "step": 542 }, { "epoch": 0.23649825783972125, "grad_norm": 2.4480040073394775, "learning_rate": 5.4801600882250335e-05, "loss": 0.5053808689117432, "step": 543 }, { "epoch": 0.23693379790940766, "grad_norm": 2.4296443462371826, "learning_rate": 5.477993760972384e-05, "loss": 0.3119818866252899, "step": 544 }, { "epoch": 0.23736933797909407, "grad_norm": 32.035987854003906, "learning_rate": 5.4758233592816205e-05, "loss": 0.3511289358139038, "step": 545 }, { "epoch": 0.23780487804878048, "grad_norm": 2.7308177947998047, "learning_rate": 5.4736488867214226e-05, "loss": 0.29788827896118164, "step": 546 }, { "epoch": 0.2382404181184669, "grad_norm": 2.649437665939331, "learning_rate": 5.4714703468671646e-05, "loss": 0.3411996364593506, "step": 547 }, { "epoch": 0.23867595818815332, "grad_norm": 2.7120471000671387, "learning_rate": 5.469287743300909e-05, "loss": 0.2743901312351227, "step": 548 }, { "epoch": 0.23911149825783973, "grad_norm": 1.9327714443206787, "learning_rate": 5.467101079611399e-05, "loss": 0.2022940218448639, "step": 549 }, { "epoch": 0.23954703832752614, "grad_norm": 2.2049081325531006, "learning_rate": 5.464910359394051e-05, "loss": 0.2971206605434418, "step": 550 }, { "epoch": 0.23998257839721254, "grad_norm": 2.5009241104125977, "learning_rate": 5.462715586250957e-05, "loss": 0.23545147478580475, "step": 551 }, { "epoch": 0.24041811846689895, "grad_norm": 2.061546802520752, "learning_rate": 5.460516763790868e-05, "loss": 0.25301986932754517, "step": 552 }, { "epoch": 0.24085365853658536, "grad_norm": 2.983513593673706, "learning_rate": 5.458313895629196e-05, "loss": 0.37645745277404785, "step": 553 }, { "epoch": 0.24128919860627177, "grad_norm": 2.133399724960327, "learning_rate": 5.456106985388003e-05, "loss": 0.24635758996009827, "step": 554 }, { "epoch": 0.2417247386759582, "grad_norm": 2.2305338382720947, "learning_rate": 5.4538960366960014e-05, "loss": 0.2812504470348358, "step": 555 }, { "epoch": 0.2421602787456446, "grad_norm": 2.751319169998169, "learning_rate": 5.4516810531885374e-05, "loss": 0.38190406560897827, "step": 556 }, { "epoch": 0.24259581881533102, "grad_norm": 2.385063648223877, "learning_rate": 5.4494620385075957e-05, "loss": 0.29792240262031555, "step": 557 }, { "epoch": 0.24303135888501742, "grad_norm": 2.248581647872925, "learning_rate": 5.44723899630179e-05, "loss": 0.21843376755714417, "step": 558 }, { "epoch": 0.24346689895470383, "grad_norm": 2.7898223400115967, "learning_rate": 5.445011930226353e-05, "loss": 0.2317291498184204, "step": 559 }, { "epoch": 0.24390243902439024, "grad_norm": 2.4398915767669678, "learning_rate": 5.442780843943135e-05, "loss": 0.40331947803497314, "step": 560 }, { "epoch": 0.24433797909407665, "grad_norm": 2.8241281509399414, "learning_rate": 5.440545741120599e-05, "loss": 0.330608069896698, "step": 561 }, { "epoch": 0.24477351916376305, "grad_norm": 2.1398751735687256, "learning_rate": 5.438306625433808e-05, "loss": 0.355224609375, "step": 562 }, { "epoch": 0.2452090592334495, "grad_norm": 2.459094524383545, "learning_rate": 5.436063500564427e-05, "loss": 0.30433890223503113, "step": 563 }, { "epoch": 0.2456445993031359, "grad_norm": 2.563917875289917, "learning_rate": 5.4338163702007076e-05, "loss": 0.3069239854812622, "step": 564 }, { "epoch": 0.2460801393728223, "grad_norm": 5.397764205932617, "learning_rate": 5.4315652380374945e-05, "loss": 0.29620981216430664, "step": 565 }, { "epoch": 0.2465156794425087, "grad_norm": 2.1989657878875732, "learning_rate": 5.4293101077762076e-05, "loss": 0.2682328224182129, "step": 566 }, { "epoch": 0.24695121951219512, "grad_norm": 2.394331216812134, "learning_rate": 5.427050983124843e-05, "loss": 0.2453674077987671, "step": 567 }, { "epoch": 0.24738675958188153, "grad_norm": 2.304926872253418, "learning_rate": 5.424787867797962e-05, "loss": 0.2651340961456299, "step": 568 }, { "epoch": 0.24782229965156793, "grad_norm": 2.7604246139526367, "learning_rate": 5.4225207655166896e-05, "loss": 0.4102301001548767, "step": 569 }, { "epoch": 0.24825783972125434, "grad_norm": 2.553823947906494, "learning_rate": 5.420249680008707e-05, "loss": 0.4071410000324249, "step": 570 }, { "epoch": 0.24869337979094078, "grad_norm": 3.386638641357422, "learning_rate": 5.4179746150082425e-05, "loss": 0.28314176201820374, "step": 571 }, { "epoch": 0.24912891986062718, "grad_norm": 2.14604115486145, "learning_rate": 5.415695574256068e-05, "loss": 0.2376149594783783, "step": 572 }, { "epoch": 0.2495644599303136, "grad_norm": 2.7643566131591797, "learning_rate": 5.413412561499497e-05, "loss": 0.4142191410064697, "step": 573 }, { "epoch": 0.25, "grad_norm": 4.561444282531738, "learning_rate": 5.411125580492366e-05, "loss": 0.48868033289909363, "step": 574 }, { "epoch": 0.25043554006968644, "grad_norm": 1.8154240846633911, "learning_rate": 5.408834634995044e-05, "loss": 0.22167183458805084, "step": 575 }, { "epoch": 0.2508710801393728, "grad_norm": 2.7428133487701416, "learning_rate": 5.4065397287744123e-05, "loss": 0.19980987906455994, "step": 576 }, { "epoch": 0.25130662020905925, "grad_norm": 2.268111228942871, "learning_rate": 5.40424086560387e-05, "loss": 0.12131068110466003, "step": 577 }, { "epoch": 0.25174216027874563, "grad_norm": 2.2367212772369385, "learning_rate": 5.401938049263319e-05, "loss": 0.2455998957157135, "step": 578 }, { "epoch": 0.25217770034843207, "grad_norm": 3.422499656677246, "learning_rate": 5.399631283539162e-05, "loss": 0.4687111973762512, "step": 579 }, { "epoch": 0.25261324041811845, "grad_norm": 3.183786153793335, "learning_rate": 5.397320572224296e-05, "loss": 0.2607903480529785, "step": 580 }, { "epoch": 0.2530487804878049, "grad_norm": 2.5269060134887695, "learning_rate": 5.395005919118105e-05, "loss": 0.2356310784816742, "step": 581 }, { "epoch": 0.2534843205574913, "grad_norm": 3.032639265060425, "learning_rate": 5.392687328026454e-05, "loss": 0.19484254717826843, "step": 582 }, { "epoch": 0.2539198606271777, "grad_norm": 2.1062393188476562, "learning_rate": 5.390364802761683e-05, "loss": 0.178542360663414, "step": 583 }, { "epoch": 0.25435540069686413, "grad_norm": 2.02070689201355, "learning_rate": 5.388038347142603e-05, "loss": 0.26222264766693115, "step": 584 }, { "epoch": 0.2547909407665505, "grad_norm": 3.2957096099853516, "learning_rate": 5.3857079649944866e-05, "loss": 0.5145093202590942, "step": 585 }, { "epoch": 0.25522648083623695, "grad_norm": 2.0789458751678467, "learning_rate": 5.383373660149058e-05, "loss": 0.24781036376953125, "step": 586 }, { "epoch": 0.2556620209059233, "grad_norm": 2.1110708713531494, "learning_rate": 5.3810354364444975e-05, "loss": 0.2414492815732956, "step": 587 }, { "epoch": 0.25609756097560976, "grad_norm": 2.3557658195495605, "learning_rate": 5.378693297725426e-05, "loss": 0.3228926360607147, "step": 588 }, { "epoch": 0.25653310104529614, "grad_norm": 2.3702940940856934, "learning_rate": 5.3763472478429014e-05, "loss": 0.4048871397972107, "step": 589 }, { "epoch": 0.2569686411149826, "grad_norm": 2.050790309906006, "learning_rate": 5.373997290654415e-05, "loss": 0.3276667296886444, "step": 590 }, { "epoch": 0.257404181184669, "grad_norm": 3.1259238719940186, "learning_rate": 5.371643430023879e-05, "loss": 0.3684636652469635, "step": 591 }, { "epoch": 0.2578397212543554, "grad_norm": 2.837117910385132, "learning_rate": 5.3692856698216274e-05, "loss": 0.41767531633377075, "step": 592 }, { "epoch": 0.2582752613240418, "grad_norm": 2.3567311763763428, "learning_rate": 5.366924013924403e-05, "loss": 0.2999117374420166, "step": 593 }, { "epoch": 0.2587108013937282, "grad_norm": 2.6026651859283447, "learning_rate": 5.364558466215356e-05, "loss": 0.3756731450557709, "step": 594 }, { "epoch": 0.25914634146341464, "grad_norm": 2.351811408996582, "learning_rate": 5.362189030584036e-05, "loss": 0.23413093388080597, "step": 595 }, { "epoch": 0.259581881533101, "grad_norm": 3.4676575660705566, "learning_rate": 5.359815710926384e-05, "loss": 0.5966187715530396, "step": 596 }, { "epoch": 0.26001742160278746, "grad_norm": 3.2534892559051514, "learning_rate": 5.3574385111447275e-05, "loss": 0.20008111000061035, "step": 597 }, { "epoch": 0.2604529616724739, "grad_norm": 2.506997585296631, "learning_rate": 5.355057435147774e-05, "loss": 0.34755295515060425, "step": 598 }, { "epoch": 0.2608885017421603, "grad_norm": 1.9204219579696655, "learning_rate": 5.352672486850607e-05, "loss": 0.35030269622802734, "step": 599 }, { "epoch": 0.2613240418118467, "grad_norm": 2.489103317260742, "learning_rate": 5.350283670174671e-05, "loss": 0.36233243346214294, "step": 600 }, { "epoch": 0.2617595818815331, "grad_norm": 2.642930507659912, "learning_rate": 5.3478909890477774e-05, "loss": 0.20768094062805176, "step": 601 }, { "epoch": 0.2621951219512195, "grad_norm": 3.5183780193328857, "learning_rate": 5.34549444740409e-05, "loss": 0.46706584095954895, "step": 602 }, { "epoch": 0.2626306620209059, "grad_norm": 3.0686042308807373, "learning_rate": 5.3430940491841166e-05, "loss": 0.4515647888183594, "step": 603 }, { "epoch": 0.26306620209059234, "grad_norm": 2.3039629459381104, "learning_rate": 5.34068979833471e-05, "loss": 0.24386319518089294, "step": 604 }, { "epoch": 0.2635017421602787, "grad_norm": 2.276005268096924, "learning_rate": 5.3382816988090574e-05, "loss": 0.3203132152557373, "step": 605 }, { "epoch": 0.26393728222996515, "grad_norm": 2.282247304916382, "learning_rate": 5.335869754566673e-05, "loss": 0.08775690197944641, "step": 606 }, { "epoch": 0.2643728222996516, "grad_norm": 2.613861560821533, "learning_rate": 5.333453969573392e-05, "loss": 0.3421464264392853, "step": 607 }, { "epoch": 0.26480836236933797, "grad_norm": 3.0887272357940674, "learning_rate": 5.331034347801367e-05, "loss": 0.28912633657455444, "step": 608 }, { "epoch": 0.2652439024390244, "grad_norm": 376.1576843261719, "learning_rate": 5.3286108932290594e-05, "loss": 5.468525409698486, "step": 609 }, { "epoch": 0.2656794425087108, "grad_norm": 4.89982795715332, "learning_rate": 5.326183609841228e-05, "loss": 0.2803078591823578, "step": 610 }, { "epoch": 0.2661149825783972, "grad_norm": 2.978179931640625, "learning_rate": 5.323752501628933e-05, "loss": 0.5056819319725037, "step": 611 }, { "epoch": 0.2665505226480836, "grad_norm": 1.9154103994369507, "learning_rate": 5.321317572589521e-05, "loss": 0.17219078540802002, "step": 612 }, { "epoch": 0.26698606271777003, "grad_norm": 3.017457962036133, "learning_rate": 5.3188788267266185e-05, "loss": 0.4502747058868408, "step": 613 }, { "epoch": 0.26742160278745647, "grad_norm": 2.443941831588745, "learning_rate": 5.316436268050133e-05, "loss": 0.3415779769420624, "step": 614 }, { "epoch": 0.26785714285714285, "grad_norm": 2.623373031616211, "learning_rate": 5.313989900576237e-05, "loss": 0.3630954623222351, "step": 615 }, { "epoch": 0.2682926829268293, "grad_norm": 3.3081037998199463, "learning_rate": 5.311539728327368e-05, "loss": 0.3723497688770294, "step": 616 }, { "epoch": 0.26872822299651566, "grad_norm": 2.7899365425109863, "learning_rate": 5.3090857553322185e-05, "loss": 0.26360979676246643, "step": 617 }, { "epoch": 0.2691637630662021, "grad_norm": 3.0934946537017822, "learning_rate": 5.306627985625729e-05, "loss": 0.42840421199798584, "step": 618 }, { "epoch": 0.2695993031358885, "grad_norm": 2.2962405681610107, "learning_rate": 5.304166423249087e-05, "loss": 0.33532169461250305, "step": 619 }, { "epoch": 0.2700348432055749, "grad_norm": 4.007911205291748, "learning_rate": 5.301701072249711e-05, "loss": 0.26176902651786804, "step": 620 }, { "epoch": 0.27047038327526135, "grad_norm": 2.2172691822052, "learning_rate": 5.299231936681253e-05, "loss": 0.22151288390159607, "step": 621 }, { "epoch": 0.27090592334494773, "grad_norm": 4.345461845397949, "learning_rate": 5.296759020603584e-05, "loss": 0.4373162090778351, "step": 622 }, { "epoch": 0.27134146341463417, "grad_norm": 2.7401859760284424, "learning_rate": 5.294282328082796e-05, "loss": 0.5318459272384644, "step": 623 }, { "epoch": 0.27177700348432055, "grad_norm": 3.560107946395874, "learning_rate": 5.291801863191184e-05, "loss": 0.28315651416778564, "step": 624 }, { "epoch": 0.272212543554007, "grad_norm": 2.404473066329956, "learning_rate": 5.289317630007252e-05, "loss": 0.2705649733543396, "step": 625 }, { "epoch": 0.27264808362369336, "grad_norm": 2.635206699371338, "learning_rate": 5.286829632615696e-05, "loss": 0.41881152987480164, "step": 626 }, { "epoch": 0.2730836236933798, "grad_norm": 2.296557664871216, "learning_rate": 5.284337875107403e-05, "loss": 0.31238576769828796, "step": 627 }, { "epoch": 0.2735191637630662, "grad_norm": 2.548466682434082, "learning_rate": 5.281842361579443e-05, "loss": 0.4516921639442444, "step": 628 }, { "epoch": 0.2739547038327526, "grad_norm": 2.0833358764648438, "learning_rate": 5.27934309613506e-05, "loss": 0.24677640199661255, "step": 629 }, { "epoch": 0.27439024390243905, "grad_norm": 1.8020131587982178, "learning_rate": 5.276840082883667e-05, "loss": 0.15432265400886536, "step": 630 }, { "epoch": 0.2748257839721254, "grad_norm": 1.9113121032714844, "learning_rate": 5.2743333259408425e-05, "loss": 0.30026715993881226, "step": 631 }, { "epoch": 0.27526132404181186, "grad_norm": 3.3054003715515137, "learning_rate": 5.271822829428316e-05, "loss": 0.3225032091140747, "step": 632 }, { "epoch": 0.27569686411149824, "grad_norm": 1.7460321187973022, "learning_rate": 5.2693085974739716e-05, "loss": 0.12103584408760071, "step": 633 }, { "epoch": 0.2761324041811847, "grad_norm": 2.3774142265319824, "learning_rate": 5.266790634211829e-05, "loss": 0.2948479950428009, "step": 634 }, { "epoch": 0.27656794425087106, "grad_norm": 2.652705192565918, "learning_rate": 5.2642689437820475e-05, "loss": 0.34239229559898376, "step": 635 }, { "epoch": 0.2770034843205575, "grad_norm": 3.548137903213501, "learning_rate": 5.261743530330913e-05, "loss": 0.5889145731925964, "step": 636 }, { "epoch": 0.2774390243902439, "grad_norm": 2.8186047077178955, "learning_rate": 5.2592143980108334e-05, "loss": 0.3608764111995697, "step": 637 }, { "epoch": 0.2778745644599303, "grad_norm": 3.5767483711242676, "learning_rate": 5.256681550980331e-05, "loss": 0.4688553214073181, "step": 638 }, { "epoch": 0.27831010452961674, "grad_norm": 2.405748128890991, "learning_rate": 5.2541449934040374e-05, "loss": 0.23952972888946533, "step": 639 }, { "epoch": 0.2787456445993031, "grad_norm": 2.519501209259033, "learning_rate": 5.251604729452683e-05, "loss": 0.363694965839386, "step": 640 }, { "epoch": 0.27918118466898956, "grad_norm": 2.459491729736328, "learning_rate": 5.249060763303095e-05, "loss": 0.32389703392982483, "step": 641 }, { "epoch": 0.27961672473867594, "grad_norm": 2.1818344593048096, "learning_rate": 5.2465130991381845e-05, "loss": 0.24412031471729279, "step": 642 }, { "epoch": 0.28005226480836237, "grad_norm": 2.9095938205718994, "learning_rate": 5.2439617411469475e-05, "loss": 0.4006360173225403, "step": 643 }, { "epoch": 0.2804878048780488, "grad_norm": 2.4606289863586426, "learning_rate": 5.2414066935244494e-05, "loss": 0.29251357913017273, "step": 644 }, { "epoch": 0.2809233449477352, "grad_norm": 2.9968316555023193, "learning_rate": 5.238847960471824e-05, "loss": 0.20299626886844635, "step": 645 }, { "epoch": 0.2813588850174216, "grad_norm": 2.781447172164917, "learning_rate": 5.236285546196266e-05, "loss": 0.43354302644729614, "step": 646 }, { "epoch": 0.281794425087108, "grad_norm": 2.7352488040924072, "learning_rate": 5.233719454911022e-05, "loss": 0.4370250701904297, "step": 647 }, { "epoch": 0.28222996515679444, "grad_norm": 2.426342010498047, "learning_rate": 5.231149690835382e-05, "loss": 0.20590318739414215, "step": 648 }, { "epoch": 0.2826655052264808, "grad_norm": 3.026993989944458, "learning_rate": 5.228576258194679e-05, "loss": 0.47881436347961426, "step": 649 }, { "epoch": 0.28310104529616725, "grad_norm": 2.2497429847717285, "learning_rate": 5.225999161220278e-05, "loss": 0.3140888810157776, "step": 650 }, { "epoch": 0.28353658536585363, "grad_norm": 2.675499200820923, "learning_rate": 5.223418404149565e-05, "loss": 0.317365825176239, "step": 651 }, { "epoch": 0.28397212543554007, "grad_norm": 4.438257217407227, "learning_rate": 5.2208339912259464e-05, "loss": 0.3303869664669037, "step": 652 }, { "epoch": 0.2844076655052265, "grad_norm": 1.9659825563430786, "learning_rate": 5.218245926698842e-05, "loss": 0.14532172679901123, "step": 653 }, { "epoch": 0.2848432055749129, "grad_norm": 2.1391022205352783, "learning_rate": 5.2156542148236725e-05, "loss": 0.3416174352169037, "step": 654 }, { "epoch": 0.2852787456445993, "grad_norm": 4.760599136352539, "learning_rate": 5.213058859861856e-05, "loss": 0.4836631119251251, "step": 655 }, { "epoch": 0.2857142857142857, "grad_norm": 2.5022330284118652, "learning_rate": 5.210459866080803e-05, "loss": 0.24194282293319702, "step": 656 }, { "epoch": 0.28614982578397213, "grad_norm": 2.1997132301330566, "learning_rate": 5.2078572377539054e-05, "loss": 0.27557626366615295, "step": 657 }, { "epoch": 0.2865853658536585, "grad_norm": 2.8470523357391357, "learning_rate": 5.20525097916053e-05, "loss": 0.3273669183254242, "step": 658 }, { "epoch": 0.28702090592334495, "grad_norm": 3.201320171356201, "learning_rate": 5.2026410945860165e-05, "loss": 0.40493515133857727, "step": 659 }, { "epoch": 0.2874564459930314, "grad_norm": 2.5041067600250244, "learning_rate": 5.200027588321664e-05, "loss": 0.24689346551895142, "step": 660 }, { "epoch": 0.28789198606271776, "grad_norm": 2.182828187942505, "learning_rate": 5.197410464664726e-05, "loss": 0.2969200611114502, "step": 661 }, { "epoch": 0.2883275261324042, "grad_norm": 2.461186408996582, "learning_rate": 5.194789727918404e-05, "loss": 0.3893936276435852, "step": 662 }, { "epoch": 0.2887630662020906, "grad_norm": 2.3307294845581055, "learning_rate": 5.1921653823918434e-05, "loss": 0.2763025760650635, "step": 663 }, { "epoch": 0.289198606271777, "grad_norm": 3.478661298751831, "learning_rate": 5.189537432400119e-05, "loss": 0.32283133268356323, "step": 664 }, { "epoch": 0.2896341463414634, "grad_norm": 2.411134958267212, "learning_rate": 5.186905882264235e-05, "loss": 0.2972927987575531, "step": 665 }, { "epoch": 0.29006968641114983, "grad_norm": 2.8395445346832275, "learning_rate": 5.184270736311115e-05, "loss": 0.3796316981315613, "step": 666 }, { "epoch": 0.2905052264808362, "grad_norm": 8.8296537399292, "learning_rate": 5.181631998873592e-05, "loss": 0.16949090361595154, "step": 667 }, { "epoch": 0.29094076655052264, "grad_norm": 2.5507495403289795, "learning_rate": 5.1789896742904096e-05, "loss": 0.18015533685684204, "step": 668 }, { "epoch": 0.2913763066202091, "grad_norm": 3.095705509185791, "learning_rate": 5.1763437669062056e-05, "loss": 0.5752538442611694, "step": 669 }, { "epoch": 0.29181184668989546, "grad_norm": 2.3496663570404053, "learning_rate": 5.1736942810715106e-05, "loss": 0.27807486057281494, "step": 670 }, { "epoch": 0.2922473867595819, "grad_norm": 2.0596489906311035, "learning_rate": 5.1710412211427364e-05, "loss": 0.3460599184036255, "step": 671 }, { "epoch": 0.2926829268292683, "grad_norm": 2.478757858276367, "learning_rate": 5.168384591482175e-05, "loss": 0.5277547836303711, "step": 672 }, { "epoch": 0.2931184668989547, "grad_norm": 3.2058627605438232, "learning_rate": 5.165724396457985e-05, "loss": 0.3609742820262909, "step": 673 }, { "epoch": 0.2935540069686411, "grad_norm": 2.436610460281372, "learning_rate": 5.163060640444191e-05, "loss": 0.15664242208003998, "step": 674 }, { "epoch": 0.2939895470383275, "grad_norm": 2.1611251831054688, "learning_rate": 5.160393327820669e-05, "loss": 0.26065748929977417, "step": 675 }, { "epoch": 0.29442508710801396, "grad_norm": 2.735788345336914, "learning_rate": 5.1577224629731446e-05, "loss": 0.48367875814437866, "step": 676 }, { "epoch": 0.29486062717770034, "grad_norm": 2.953071355819702, "learning_rate": 5.155048050293183e-05, "loss": 0.43283146619796753, "step": 677 }, { "epoch": 0.2952961672473868, "grad_norm": 2.9070985317230225, "learning_rate": 5.152370094178185e-05, "loss": 0.2484615296125412, "step": 678 }, { "epoch": 0.29573170731707316, "grad_norm": 2.499534845352173, "learning_rate": 5.1496885990313765e-05, "loss": 0.3429194688796997, "step": 679 }, { "epoch": 0.2961672473867596, "grad_norm": 3.2010867595672607, "learning_rate": 5.147003569261803e-05, "loss": 0.5093741416931152, "step": 680 }, { "epoch": 0.29660278745644597, "grad_norm": 1.9604192972183228, "learning_rate": 5.14431500928432e-05, "loss": 0.17249713838100433, "step": 681 }, { "epoch": 0.2970383275261324, "grad_norm": 2.3224704265594482, "learning_rate": 5.141622923519589e-05, "loss": 0.35473430156707764, "step": 682 }, { "epoch": 0.29747386759581884, "grad_norm": 2.3144235610961914, "learning_rate": 5.1389273163940705e-05, "loss": 0.3599074184894562, "step": 683 }, { "epoch": 0.2979094076655052, "grad_norm": 2.9257864952087402, "learning_rate": 5.1362281923400105e-05, "loss": 0.6347458362579346, "step": 684 }, { "epoch": 0.29834494773519166, "grad_norm": 1.9177112579345703, "learning_rate": 5.133525555795442e-05, "loss": 0.2666842043399811, "step": 685 }, { "epoch": 0.29878048780487804, "grad_norm": 1.803248643875122, "learning_rate": 5.130819411204171e-05, "loss": 0.19426755607128143, "step": 686 }, { "epoch": 0.29921602787456447, "grad_norm": 2.1470141410827637, "learning_rate": 5.1281097630157735e-05, "loss": 0.1968349814414978, "step": 687 }, { "epoch": 0.29965156794425085, "grad_norm": 1.4250452518463135, "learning_rate": 5.125396615685584e-05, "loss": 0.15600012242794037, "step": 688 }, { "epoch": 0.3000871080139373, "grad_norm": 2.9089303016662598, "learning_rate": 5.122679973674691e-05, "loss": 0.35807380080223083, "step": 689 }, { "epoch": 0.30052264808362367, "grad_norm": 2.1265149116516113, "learning_rate": 5.1199598414499304e-05, "loss": 0.22464460134506226, "step": 690 }, { "epoch": 0.3009581881533101, "grad_norm": 1.9009349346160889, "learning_rate": 5.1172362234838774e-05, "loss": 0.2140391767024994, "step": 691 }, { "epoch": 0.30139372822299654, "grad_norm": 2.1035664081573486, "learning_rate": 5.114509124254835e-05, "loss": 0.32412955164909363, "step": 692 }, { "epoch": 0.3018292682926829, "grad_norm": 2.8171448707580566, "learning_rate": 5.1117785482468347e-05, "loss": 0.30770960450172424, "step": 693 }, { "epoch": 0.30226480836236935, "grad_norm": 3.4874441623687744, "learning_rate": 5.109044499949622e-05, "loss": 0.4037453532218933, "step": 694 }, { "epoch": 0.30270034843205573, "grad_norm": 2.3737778663635254, "learning_rate": 5.106306983858652e-05, "loss": 0.26509037613868713, "step": 695 }, { "epoch": 0.30313588850174217, "grad_norm": 2.5832784175872803, "learning_rate": 5.1035660044750825e-05, "loss": 0.5186740159988403, "step": 696 }, { "epoch": 0.30357142857142855, "grad_norm": 5.652341842651367, "learning_rate": 5.1008215663057654e-05, "loss": 0.2192973494529724, "step": 697 }, { "epoch": 0.304006968641115, "grad_norm": 1.8420180082321167, "learning_rate": 5.098073673863239e-05, "loss": 0.14051344990730286, "step": 698 }, { "epoch": 0.3044425087108014, "grad_norm": 2.808130979537964, "learning_rate": 5.0953223316657224e-05, "loss": 0.45707449316978455, "step": 699 }, { "epoch": 0.3048780487804878, "grad_norm": 2.0046088695526123, "learning_rate": 5.092567544237108e-05, "loss": 0.2464665323495865, "step": 700 }, { "epoch": 0.30531358885017423, "grad_norm": 6.972399711608887, "learning_rate": 5.089809316106948e-05, "loss": 0.48700714111328125, "step": 701 }, { "epoch": 0.3057491289198606, "grad_norm": 2.7439234256744385, "learning_rate": 5.08704765181046e-05, "loss": 0.36247894167900085, "step": 702 }, { "epoch": 0.30618466898954705, "grad_norm": 2.1775777339935303, "learning_rate": 5.084282555888503e-05, "loss": 0.3424620032310486, "step": 703 }, { "epoch": 0.30662020905923343, "grad_norm": 1.7375322580337524, "learning_rate": 5.0815140328875846e-05, "loss": 0.23459231853485107, "step": 704 }, { "epoch": 0.30705574912891986, "grad_norm": 2.7831716537475586, "learning_rate": 5.078742087359845e-05, "loss": 0.4608604311943054, "step": 705 }, { "epoch": 0.3074912891986063, "grad_norm": 1.9066694974899292, "learning_rate": 5.075966723863052e-05, "loss": 0.213066965341568, "step": 706 }, { "epoch": 0.3079268292682927, "grad_norm": 2.277796983718872, "learning_rate": 5.0731879469605946e-05, "loss": 0.3741539418697357, "step": 707 }, { "epoch": 0.3083623693379791, "grad_norm": 2.268251895904541, "learning_rate": 5.07040576122147e-05, "loss": 0.17553524672985077, "step": 708 }, { "epoch": 0.3087979094076655, "grad_norm": 3.7960548400878906, "learning_rate": 5.067620171220288e-05, "loss": 0.18264701962471008, "step": 709 }, { "epoch": 0.30923344947735193, "grad_norm": 5.125026226043701, "learning_rate": 5.064831181537248e-05, "loss": 0.42962655425071716, "step": 710 }, { "epoch": 0.3096689895470383, "grad_norm": 2.597109317779541, "learning_rate": 5.062038796758144e-05, "loss": 0.2502005994319916, "step": 711 }, { "epoch": 0.31010452961672474, "grad_norm": 1.9201244115829468, "learning_rate": 5.0592430214743515e-05, "loss": 0.24686509370803833, "step": 712 }, { "epoch": 0.3105400696864111, "grad_norm": 2.0413641929626465, "learning_rate": 5.056443860282819e-05, "loss": 0.2410474270582199, "step": 713 }, { "epoch": 0.31097560975609756, "grad_norm": 2.6316041946411133, "learning_rate": 5.0536413177860664e-05, "loss": 0.3609340786933899, "step": 714 }, { "epoch": 0.311411149825784, "grad_norm": 2.3200836181640625, "learning_rate": 5.0508353985921675e-05, "loss": 0.41137173771858215, "step": 715 }, { "epoch": 0.3118466898954704, "grad_norm": 2.083667516708374, "learning_rate": 5.048026107314754e-05, "loss": 0.26973897218704224, "step": 716 }, { "epoch": 0.3122822299651568, "grad_norm": 2.274315595626831, "learning_rate": 5.0452134485729984e-05, "loss": 0.43835991621017456, "step": 717 }, { "epoch": 0.3127177700348432, "grad_norm": 3.3288512229919434, "learning_rate": 5.042397426991612e-05, "loss": 0.7102029323577881, "step": 718 }, { "epoch": 0.3131533101045296, "grad_norm": 1.8666402101516724, "learning_rate": 5.039578047200833e-05, "loss": 0.20567335188388824, "step": 719 }, { "epoch": 0.313588850174216, "grad_norm": 2.454479455947876, "learning_rate": 5.036755313836425e-05, "loss": 0.3354480266571045, "step": 720 }, { "epoch": 0.31402439024390244, "grad_norm": 2.1819119453430176, "learning_rate": 5.033929231539663e-05, "loss": 0.18905246257781982, "step": 721 }, { "epoch": 0.3144599303135889, "grad_norm": 2.4131298065185547, "learning_rate": 5.031099804957329e-05, "loss": 0.2505360543727875, "step": 722 }, { "epoch": 0.31489547038327526, "grad_norm": 1.9293185472488403, "learning_rate": 5.028267038741704e-05, "loss": 0.3186812400817871, "step": 723 }, { "epoch": 0.3153310104529617, "grad_norm": 2.3936076164245605, "learning_rate": 5.025430937550561e-05, "loss": 0.33607974648475647, "step": 724 }, { "epoch": 0.31576655052264807, "grad_norm": 1.7327818870544434, "learning_rate": 5.022591506047155e-05, "loss": 0.17973336577415466, "step": 725 }, { "epoch": 0.3162020905923345, "grad_norm": 2.929656982421875, "learning_rate": 5.019748748900219e-05, "loss": 0.317905992269516, "step": 726 }, { "epoch": 0.3166376306620209, "grad_norm": 2.2508792877197266, "learning_rate": 5.0169026707839506e-05, "loss": 0.20367415249347687, "step": 727 }, { "epoch": 0.3170731707317073, "grad_norm": 1.5391528606414795, "learning_rate": 5.014053276378012e-05, "loss": 0.20586152374744415, "step": 728 }, { "epoch": 0.3175087108013937, "grad_norm": 2.805774211883545, "learning_rate": 5.011200570367516e-05, "loss": 0.3137643039226532, "step": 729 }, { "epoch": 0.31794425087108014, "grad_norm": 2.854203939437866, "learning_rate": 5.0083445574430205e-05, "loss": 0.5275669693946838, "step": 730 }, { "epoch": 0.31837979094076657, "grad_norm": 2.0014233589172363, "learning_rate": 5.0054852423005214e-05, "loss": 0.21874453127384186, "step": 731 }, { "epoch": 0.31881533101045295, "grad_norm": 1.589391827583313, "learning_rate": 5.002622629641444e-05, "loss": 0.15347574651241302, "step": 732 }, { "epoch": 0.3192508710801394, "grad_norm": 1.7128846645355225, "learning_rate": 4.999756724172635e-05, "loss": 0.20001181960105896, "step": 733 }, { "epoch": 0.31968641114982577, "grad_norm": 2.4763033390045166, "learning_rate": 4.996887530606357e-05, "loss": 0.30398374795913696, "step": 734 }, { "epoch": 0.3201219512195122, "grad_norm": 2.8564631938934326, "learning_rate": 4.9940150536602775e-05, "loss": 0.45606327056884766, "step": 735 }, { "epoch": 0.3205574912891986, "grad_norm": 4.005936145782471, "learning_rate": 4.991139298057461e-05, "loss": 0.2508484125137329, "step": 736 }, { "epoch": 0.320993031358885, "grad_norm": 2.3788046836853027, "learning_rate": 4.988260268526369e-05, "loss": 0.30009037256240845, "step": 737 }, { "epoch": 0.32142857142857145, "grad_norm": 2.2980520725250244, "learning_rate": 4.985377969800839e-05, "loss": 0.29453277587890625, "step": 738 }, { "epoch": 0.32186411149825783, "grad_norm": 1.8585875034332275, "learning_rate": 4.982492406620088e-05, "loss": 0.21691131591796875, "step": 739 }, { "epoch": 0.32229965156794427, "grad_norm": 2.273920774459839, "learning_rate": 4.9796035837287004e-05, "loss": 0.3003171980381012, "step": 740 }, { "epoch": 0.32273519163763065, "grad_norm": 2.0973970890045166, "learning_rate": 4.9767115058766185e-05, "loss": 0.24099519848823547, "step": 741 }, { "epoch": 0.3231707317073171, "grad_norm": 4.521590232849121, "learning_rate": 4.9738161778191386e-05, "loss": 0.36588922142982483, "step": 742 }, { "epoch": 0.32360627177700346, "grad_norm": 2.3793509006500244, "learning_rate": 4.970917604316898e-05, "loss": 0.37052589654922485, "step": 743 }, { "epoch": 0.3240418118466899, "grad_norm": 2.894683361053467, "learning_rate": 4.9680157901358755e-05, "loss": 0.4240562617778778, "step": 744 }, { "epoch": 0.32447735191637633, "grad_norm": 4.382136821746826, "learning_rate": 4.9651107400473744e-05, "loss": 0.5023569464683533, "step": 745 }, { "epoch": 0.3249128919860627, "grad_norm": 3.023576021194458, "learning_rate": 4.962202458828018e-05, "loss": 0.4053381085395813, "step": 746 }, { "epoch": 0.32534843205574915, "grad_norm": 2.969442129135132, "learning_rate": 4.959290951259746e-05, "loss": 0.4567044675350189, "step": 747 }, { "epoch": 0.32578397212543553, "grad_norm": 1.7953426837921143, "learning_rate": 4.9563762221298e-05, "loss": 0.14316818118095398, "step": 748 }, { "epoch": 0.32621951219512196, "grad_norm": 2.970860719680786, "learning_rate": 4.9534582762307205e-05, "loss": 0.5485292077064514, "step": 749 }, { "epoch": 0.32665505226480834, "grad_norm": 2.4259376525878906, "learning_rate": 4.950537118360336e-05, "loss": 0.23485639691352844, "step": 750 }, { "epoch": 0.3270905923344948, "grad_norm": 2.2285311222076416, "learning_rate": 4.947612753321756e-05, "loss": 0.31871992349624634, "step": 751 }, { "epoch": 0.32752613240418116, "grad_norm": 2.3286125659942627, "learning_rate": 4.944685185923366e-05, "loss": 0.13518506288528442, "step": 752 }, { "epoch": 0.3279616724738676, "grad_norm": 3.056697130203247, "learning_rate": 4.941754420978812e-05, "loss": 0.1707652062177658, "step": 753 }, { "epoch": 0.32839721254355403, "grad_norm": 2.178298234939575, "learning_rate": 4.9388204633070026e-05, "loss": 0.16916383802890778, "step": 754 }, { "epoch": 0.3288327526132404, "grad_norm": 2.166531801223755, "learning_rate": 4.9358833177320936e-05, "loss": 0.22334544360637665, "step": 755 }, { "epoch": 0.32926829268292684, "grad_norm": 2.549420118331909, "learning_rate": 4.932942989083483e-05, "loss": 0.4987979829311371, "step": 756 }, { "epoch": 0.3297038327526132, "grad_norm": 1.3684957027435303, "learning_rate": 4.9299994821958023e-05, "loss": 0.14485366642475128, "step": 757 }, { "epoch": 0.33013937282229966, "grad_norm": 1.5360108613967896, "learning_rate": 4.927052801908909e-05, "loss": 0.1815292239189148, "step": 758 }, { "epoch": 0.33057491289198604, "grad_norm": 2.047179698944092, "learning_rate": 4.9241029530678784e-05, "loss": 0.2976647913455963, "step": 759 }, { "epoch": 0.3310104529616725, "grad_norm": 1.785902738571167, "learning_rate": 4.921149940522995e-05, "loss": 0.26233765482902527, "step": 760 }, { "epoch": 0.3314459930313589, "grad_norm": 2.2606799602508545, "learning_rate": 4.918193769129748e-05, "loss": 0.2813410460948944, "step": 761 }, { "epoch": 0.3318815331010453, "grad_norm": 2.012852907180786, "learning_rate": 4.915234443748817e-05, "loss": 0.2680850923061371, "step": 762 }, { "epoch": 0.3323170731707317, "grad_norm": 1.916207194328308, "learning_rate": 4.912271969246069e-05, "loss": 0.17596393823623657, "step": 763 }, { "epoch": 0.3327526132404181, "grad_norm": 2.380300521850586, "learning_rate": 4.90930635049255e-05, "loss": 0.32600095868110657, "step": 764 }, { "epoch": 0.33318815331010454, "grad_norm": 2.1763343811035156, "learning_rate": 4.906337592364473e-05, "loss": 0.1971885859966278, "step": 765 }, { "epoch": 0.3336236933797909, "grad_norm": 2.123842477798462, "learning_rate": 4.903365699743216e-05, "loss": 0.3027835190296173, "step": 766 }, { "epoch": 0.33405923344947736, "grad_norm": 2.117567777633667, "learning_rate": 4.9003906775153104e-05, "loss": 0.2675943076610565, "step": 767 }, { "epoch": 0.3344947735191638, "grad_norm": 1.8731281757354736, "learning_rate": 4.897412530572431e-05, "loss": 0.21540436148643494, "step": 768 }, { "epoch": 0.33493031358885017, "grad_norm": 2.385281562805176, "learning_rate": 4.8944312638113936e-05, "loss": 0.3476840555667877, "step": 769 }, { "epoch": 0.3353658536585366, "grad_norm": 2.5160634517669678, "learning_rate": 4.8914468821341415e-05, "loss": 0.2747837007045746, "step": 770 }, { "epoch": 0.335801393728223, "grad_norm": 1.995218276977539, "learning_rate": 4.888459390447741e-05, "loss": 0.29531779885292053, "step": 771 }, { "epoch": 0.3362369337979094, "grad_norm": 2.7136850357055664, "learning_rate": 4.885468793664371e-05, "loss": 0.3939990699291229, "step": 772 }, { "epoch": 0.3366724738675958, "grad_norm": 2.2970094680786133, "learning_rate": 4.882475096701317e-05, "loss": 0.30190250277519226, "step": 773 }, { "epoch": 0.33710801393728224, "grad_norm": 1.8993784189224243, "learning_rate": 4.879478304480962e-05, "loss": 0.26041510701179504, "step": 774 }, { "epoch": 0.3375435540069686, "grad_norm": 3.246617555618286, "learning_rate": 4.876478421930776e-05, "loss": 0.2988961935043335, "step": 775 }, { "epoch": 0.33797909407665505, "grad_norm": 1.6249643564224243, "learning_rate": 4.873475453983314e-05, "loss": 0.1617831438779831, "step": 776 }, { "epoch": 0.3384146341463415, "grad_norm": 2.038904905319214, "learning_rate": 4.870469405576201e-05, "loss": 0.22303509712219238, "step": 777 }, { "epoch": 0.33885017421602787, "grad_norm": 3.2666096687316895, "learning_rate": 4.8674602816521284e-05, "loss": 0.20506058633327484, "step": 778 }, { "epoch": 0.3392857142857143, "grad_norm": 1.8270618915557861, "learning_rate": 4.8644480871588456e-05, "loss": 0.17013514041900635, "step": 779 }, { "epoch": 0.3397212543554007, "grad_norm": 2.8056349754333496, "learning_rate": 4.8614328270491484e-05, "loss": 0.4606097936630249, "step": 780 }, { "epoch": 0.3401567944250871, "grad_norm": 3.236732006072998, "learning_rate": 4.8584145062808744e-05, "loss": 0.3603575825691223, "step": 781 }, { "epoch": 0.3405923344947735, "grad_norm": 2.4107377529144287, "learning_rate": 4.855393129816895e-05, "loss": 0.5446003675460815, "step": 782 }, { "epoch": 0.34102787456445993, "grad_norm": 3.174638509750366, "learning_rate": 4.852368702625103e-05, "loss": 0.19237878918647766, "step": 783 }, { "epoch": 0.34146341463414637, "grad_norm": 2.007488250732422, "learning_rate": 4.8493412296784094e-05, "loss": 0.1635846495628357, "step": 784 }, { "epoch": 0.34189895470383275, "grad_norm": 2.6916699409484863, "learning_rate": 4.846310715954734e-05, "loss": 0.2995496392250061, "step": 785 }, { "epoch": 0.3423344947735192, "grad_norm": 2.0276548862457275, "learning_rate": 4.843277166436995e-05, "loss": 0.3006119132041931, "step": 786 }, { "epoch": 0.34277003484320556, "grad_norm": 2.308098077774048, "learning_rate": 4.8402405861131e-05, "loss": 0.2775416374206543, "step": 787 }, { "epoch": 0.343205574912892, "grad_norm": 2.6866931915283203, "learning_rate": 4.8372009799759444e-05, "loss": 0.21514524519443512, "step": 788 }, { "epoch": 0.3436411149825784, "grad_norm": 1.6504535675048828, "learning_rate": 4.834158353023397e-05, "loss": 0.17605851590633392, "step": 789 }, { "epoch": 0.3440766550522648, "grad_norm": 3.001971483230591, "learning_rate": 4.831112710258292e-05, "loss": 0.3435129225254059, "step": 790 }, { "epoch": 0.3445121951219512, "grad_norm": 2.3672101497650146, "learning_rate": 4.828064056688425e-05, "loss": 0.37349751591682434, "step": 791 }, { "epoch": 0.34494773519163763, "grad_norm": 3.3694398403167725, "learning_rate": 4.82501239732654e-05, "loss": 0.29241520166397095, "step": 792 }, { "epoch": 0.34538327526132406, "grad_norm": 1.7382696866989136, "learning_rate": 4.821957737190323e-05, "loss": 0.2380804717540741, "step": 793 }, { "epoch": 0.34581881533101044, "grad_norm": 1.8435139656066895, "learning_rate": 4.8189000813023974e-05, "loss": 0.1665818989276886, "step": 794 }, { "epoch": 0.3462543554006969, "grad_norm": 3.804211139678955, "learning_rate": 4.815839434690309e-05, "loss": 0.21870584785938263, "step": 795 }, { "epoch": 0.34668989547038326, "grad_norm": 2.9439947605133057, "learning_rate": 4.812775802386522e-05, "loss": 0.5781724452972412, "step": 796 }, { "epoch": 0.3471254355400697, "grad_norm": 2.6496896743774414, "learning_rate": 4.809709189428409e-05, "loss": 0.6180941462516785, "step": 797 }, { "epoch": 0.3475609756097561, "grad_norm": 1.6901885271072388, "learning_rate": 4.806639600858247e-05, "loss": 0.22962598502635956, "step": 798 }, { "epoch": 0.3479965156794425, "grad_norm": 1.6468688249588013, "learning_rate": 4.8035670417232e-05, "loss": 0.17219378054141998, "step": 799 }, { "epoch": 0.34843205574912894, "grad_norm": 2.349210262298584, "learning_rate": 4.800491517075322e-05, "loss": 0.2877485454082489, "step": 800 }, { "epoch": 0.3488675958188153, "grad_norm": 1.653975248336792, "learning_rate": 4.79741303197154e-05, "loss": 0.21996523439884186, "step": 801 }, { "epoch": 0.34930313588850176, "grad_norm": 2.7227258682250977, "learning_rate": 4.794331591473648e-05, "loss": 0.4063904285430908, "step": 802 }, { "epoch": 0.34973867595818814, "grad_norm": 2.049790143966675, "learning_rate": 4.7912472006483017e-05, "loss": 0.29521843791007996, "step": 803 }, { "epoch": 0.3501742160278746, "grad_norm": 2.041923999786377, "learning_rate": 4.7881598645670075e-05, "loss": 0.18165485560894012, "step": 804 }, { "epoch": 0.35060975609756095, "grad_norm": 2.8233280181884766, "learning_rate": 4.785069588306111e-05, "loss": 0.2750641703605652, "step": 805 }, { "epoch": 0.3510452961672474, "grad_norm": 2.004594564437866, "learning_rate": 4.781976376946799e-05, "loss": 0.2630676329135895, "step": 806 }, { "epoch": 0.3514808362369338, "grad_norm": 2.5958309173583984, "learning_rate": 4.778880235575077e-05, "loss": 0.3713662922382355, "step": 807 }, { "epoch": 0.3519163763066202, "grad_norm": 2.6400725841522217, "learning_rate": 4.775781169281774e-05, "loss": 0.47602757811546326, "step": 808 }, { "epoch": 0.35235191637630664, "grad_norm": 2.361229658126831, "learning_rate": 4.772679183162524e-05, "loss": 0.3832179307937622, "step": 809 }, { "epoch": 0.352787456445993, "grad_norm": 1.9195042848587036, "learning_rate": 4.769574282317765e-05, "loss": 0.2526417374610901, "step": 810 }, { "epoch": 0.35322299651567945, "grad_norm": 2.1501147747039795, "learning_rate": 4.766466471852726e-05, "loss": 0.32173803448677063, "step": 811 }, { "epoch": 0.35365853658536583, "grad_norm": 2.6281814575195312, "learning_rate": 4.7633557568774194e-05, "loss": 0.2847055494785309, "step": 812 }, { "epoch": 0.35409407665505227, "grad_norm": 2.34344744682312, "learning_rate": 4.7602421425066355e-05, "loss": 0.4627992510795593, "step": 813 }, { "epoch": 0.35452961672473865, "grad_norm": 1.4984525442123413, "learning_rate": 4.757125633859931e-05, "loss": 0.10671970993280411, "step": 814 }, { "epoch": 0.3549651567944251, "grad_norm": 2.170597553253174, "learning_rate": 4.7540062360616205e-05, "loss": 0.2696705758571625, "step": 815 }, { "epoch": 0.3554006968641115, "grad_norm": 2.531949520111084, "learning_rate": 4.750883954240771e-05, "loss": 0.41582998633384705, "step": 816 }, { "epoch": 0.3558362369337979, "grad_norm": 2.235222101211548, "learning_rate": 4.7477587935311885e-05, "loss": 0.24640201032161713, "step": 817 }, { "epoch": 0.35627177700348434, "grad_norm": 1.8476630449295044, "learning_rate": 4.744630759071416e-05, "loss": 0.17049409449100494, "step": 818 }, { "epoch": 0.3567073170731707, "grad_norm": 2.273088216781616, "learning_rate": 4.741499856004721e-05, "loss": 0.1715134233236313, "step": 819 }, { "epoch": 0.35714285714285715, "grad_norm": 1.9884344339370728, "learning_rate": 4.738366089479085e-05, "loss": 0.2179429531097412, "step": 820 }, { "epoch": 0.35757839721254353, "grad_norm": 1.775165319442749, "learning_rate": 4.7352294646472006e-05, "loss": 0.13170787692070007, "step": 821 }, { "epoch": 0.35801393728222997, "grad_norm": 2.2568187713623047, "learning_rate": 4.732089986666459e-05, "loss": 0.31695109605789185, "step": 822 }, { "epoch": 0.3584494773519164, "grad_norm": 7.905406475067139, "learning_rate": 4.728947660698943e-05, "loss": 0.7050952911376953, "step": 823 }, { "epoch": 0.3588850174216028, "grad_norm": 2.2587032318115234, "learning_rate": 4.725802491911418e-05, "loss": 0.2926887273788452, "step": 824 }, { "epoch": 0.3593205574912892, "grad_norm": 1.8203696012496948, "learning_rate": 4.7226544854753246e-05, "loss": 0.26601338386535645, "step": 825 }, { "epoch": 0.3597560975609756, "grad_norm": 2.185535192489624, "learning_rate": 4.719503646566767e-05, "loss": 0.33747395873069763, "step": 826 }, { "epoch": 0.36019163763066203, "grad_norm": 2.108612060546875, "learning_rate": 4.716349980366509e-05, "loss": 0.27849528193473816, "step": 827 }, { "epoch": 0.3606271777003484, "grad_norm": 2.727937698364258, "learning_rate": 4.7131934920599624e-05, "loss": 0.3729945719242096, "step": 828 }, { "epoch": 0.36106271777003485, "grad_norm": 2.2429885864257812, "learning_rate": 4.710034186837179e-05, "loss": 0.2559064030647278, "step": 829 }, { "epoch": 0.3614982578397213, "grad_norm": 2.595430612564087, "learning_rate": 4.706872069892842e-05, "loss": 0.1997009664773941, "step": 830 }, { "epoch": 0.36193379790940766, "grad_norm": 2.3698348999023438, "learning_rate": 4.7037071464262585e-05, "loss": 0.21821241080760956, "step": 831 }, { "epoch": 0.3623693379790941, "grad_norm": 3.0654587745666504, "learning_rate": 4.70053942164135e-05, "loss": 0.48292678594589233, "step": 832 }, { "epoch": 0.3628048780487805, "grad_norm": 2.100109815597534, "learning_rate": 4.697368900746644e-05, "loss": 0.3548566401004791, "step": 833 }, { "epoch": 0.3632404181184669, "grad_norm": 1.520383596420288, "learning_rate": 4.6941955889552655e-05, "loss": 0.150685116648674, "step": 834 }, { "epoch": 0.3636759581881533, "grad_norm": 2.9962422847747803, "learning_rate": 4.691019491484927e-05, "loss": 0.5536919236183167, "step": 835 }, { "epoch": 0.3641114982578397, "grad_norm": 1.5012987852096558, "learning_rate": 4.6878406135579256e-05, "loss": 0.12082011997699738, "step": 836 }, { "epoch": 0.3645470383275261, "grad_norm": 1.7148158550262451, "learning_rate": 4.684658960401124e-05, "loss": 0.20840385556221008, "step": 837 }, { "epoch": 0.36498257839721254, "grad_norm": 2.415844202041626, "learning_rate": 4.6814745372459544e-05, "loss": 0.23237290978431702, "step": 838 }, { "epoch": 0.365418118466899, "grad_norm": 1.80989670753479, "learning_rate": 4.678287349328399e-05, "loss": 0.25620025396347046, "step": 839 }, { "epoch": 0.36585365853658536, "grad_norm": 2.3795692920684814, "learning_rate": 4.6750974018889874e-05, "loss": 0.35787680745124817, "step": 840 }, { "epoch": 0.3662891986062718, "grad_norm": 2.517714023590088, "learning_rate": 4.671904700172787e-05, "loss": 0.37427693605422974, "step": 841 }, { "epoch": 0.3667247386759582, "grad_norm": 2.251675605773926, "learning_rate": 4.6687092494293944e-05, "loss": 0.20893049240112305, "step": 842 }, { "epoch": 0.3671602787456446, "grad_norm": 2.2461068630218506, "learning_rate": 4.665511054912925e-05, "loss": 0.30002468824386597, "step": 843 }, { "epoch": 0.367595818815331, "grad_norm": 2.0128045082092285, "learning_rate": 4.6623101218820046e-05, "loss": 0.2909575402736664, "step": 844 }, { "epoch": 0.3680313588850174, "grad_norm": 2.517052412033081, "learning_rate": 4.659106455599765e-05, "loss": 0.15982338786125183, "step": 845 }, { "epoch": 0.36846689895470386, "grad_norm": 2.331834316253662, "learning_rate": 4.655900061333829e-05, "loss": 0.34930112957954407, "step": 846 }, { "epoch": 0.36890243902439024, "grad_norm": 1.9253557920455933, "learning_rate": 4.6526909443563075e-05, "loss": 0.17883646488189697, "step": 847 }, { "epoch": 0.3693379790940767, "grad_norm": 1.4028785228729248, "learning_rate": 4.6494791099437876e-05, "loss": 0.12381847947835922, "step": 848 }, { "epoch": 0.36977351916376305, "grad_norm": 2.1856231689453125, "learning_rate": 4.646264563377323e-05, "loss": 0.3212660849094391, "step": 849 }, { "epoch": 0.3702090592334495, "grad_norm": 2.0202670097351074, "learning_rate": 4.643047309942427e-05, "loss": 0.31043222546577454, "step": 850 }, { "epoch": 0.37064459930313587, "grad_norm": 4.5791730880737305, "learning_rate": 4.639827354929065e-05, "loss": 0.20062652230262756, "step": 851 }, { "epoch": 0.3710801393728223, "grad_norm": 1.8765974044799805, "learning_rate": 4.636604703631646e-05, "loss": 0.12009351700544357, "step": 852 }, { "epoch": 0.3715156794425087, "grad_norm": 2.1494240760803223, "learning_rate": 4.633379361349008e-05, "loss": 0.24129889905452728, "step": 853 }, { "epoch": 0.3719512195121951, "grad_norm": 2.0562222003936768, "learning_rate": 4.630151333384418e-05, "loss": 0.2728952467441559, "step": 854 }, { "epoch": 0.37238675958188155, "grad_norm": 1.562795877456665, "learning_rate": 4.6269206250455544e-05, "loss": 0.20648470520973206, "step": 855 }, { "epoch": 0.37282229965156793, "grad_norm": 2.0476596355438232, "learning_rate": 4.623687241644506e-05, "loss": 0.29676952958106995, "step": 856 }, { "epoch": 0.37325783972125437, "grad_norm": 1.8746294975280762, "learning_rate": 4.620451188497761e-05, "loss": 0.2097632735967636, "step": 857 }, { "epoch": 0.37369337979094075, "grad_norm": 2.6812257766723633, "learning_rate": 4.617212470926194e-05, "loss": 0.1916254162788391, "step": 858 }, { "epoch": 0.3741289198606272, "grad_norm": 2.8972885608673096, "learning_rate": 4.613971094255063e-05, "loss": 0.49081873893737793, "step": 859 }, { "epoch": 0.37456445993031356, "grad_norm": 1.9234166145324707, "learning_rate": 4.610727063813997e-05, "loss": 0.2887973487377167, "step": 860 }, { "epoch": 0.375, "grad_norm": 1.4788038730621338, "learning_rate": 4.60748038493699e-05, "loss": 0.10276740044355392, "step": 861 }, { "epoch": 0.37543554006968644, "grad_norm": 2.112279176712036, "learning_rate": 4.604231062962389e-05, "loss": 0.29371023178100586, "step": 862 }, { "epoch": 0.3758710801393728, "grad_norm": 2.5955822467803955, "learning_rate": 4.600979103232887e-05, "loss": 0.342989444732666, "step": 863 }, { "epoch": 0.37630662020905925, "grad_norm": 2.2624590396881104, "learning_rate": 4.597724511095515e-05, "loss": 0.31010106205940247, "step": 864 }, { "epoch": 0.37674216027874563, "grad_norm": 3.920708656311035, "learning_rate": 4.594467291901634e-05, "loss": 0.34923437237739563, "step": 865 }, { "epoch": 0.37717770034843207, "grad_norm": 2.5577876567840576, "learning_rate": 4.591207451006919e-05, "loss": 0.35567763447761536, "step": 866 }, { "epoch": 0.37761324041811845, "grad_norm": 2.2601115703582764, "learning_rate": 4.5879449937713625e-05, "loss": 0.37643715739250183, "step": 867 }, { "epoch": 0.3780487804878049, "grad_norm": 2.651115894317627, "learning_rate": 4.584679925559254e-05, "loss": 0.2969552278518677, "step": 868 }, { "epoch": 0.3784843205574913, "grad_norm": 1.9528902769088745, "learning_rate": 4.581412251739177e-05, "loss": 0.21172142028808594, "step": 869 }, { "epoch": 0.3789198606271777, "grad_norm": 2.0835535526275635, "learning_rate": 4.578141977684002e-05, "loss": 0.24634137749671936, "step": 870 }, { "epoch": 0.37935540069686413, "grad_norm": 1.74702787399292, "learning_rate": 4.574869108770871e-05, "loss": 0.19275891780853271, "step": 871 }, { "epoch": 0.3797909407665505, "grad_norm": 2.2658638954162598, "learning_rate": 4.5715936503811964e-05, "loss": 0.33438411355018616, "step": 872 }, { "epoch": 0.38022648083623695, "grad_norm": 1.542203426361084, "learning_rate": 4.5683156079006466e-05, "loss": 0.16634584963321686, "step": 873 }, { "epoch": 0.3806620209059233, "grad_norm": 2.426499128341675, "learning_rate": 4.565034986719136e-05, "loss": 0.36716070771217346, "step": 874 }, { "epoch": 0.38109756097560976, "grad_norm": 2.161501407623291, "learning_rate": 4.561751792230826e-05, "loss": 0.2952579855918884, "step": 875 }, { "epoch": 0.38153310104529614, "grad_norm": 2.9603166580200195, "learning_rate": 4.558466029834102e-05, "loss": 0.17678497731685638, "step": 876 }, { "epoch": 0.3819686411149826, "grad_norm": 2.9551875591278076, "learning_rate": 4.555177704931576e-05, "loss": 0.45397627353668213, "step": 877 }, { "epoch": 0.382404181184669, "grad_norm": 2.2442197799682617, "learning_rate": 4.5518868229300704e-05, "loss": 0.15878188610076904, "step": 878 }, { "epoch": 0.3828397212543554, "grad_norm": 1.7353442907333374, "learning_rate": 4.548593389240616e-05, "loss": 0.20920580625534058, "step": 879 }, { "epoch": 0.3832752613240418, "grad_norm": 1.9834926128387451, "learning_rate": 4.545297409278435e-05, "loss": 0.18969261646270752, "step": 880 }, { "epoch": 0.3837108013937282, "grad_norm": 2.330472946166992, "learning_rate": 4.5419988884629395e-05, "loss": 0.3659213185310364, "step": 881 }, { "epoch": 0.38414634146341464, "grad_norm": 2.618563175201416, "learning_rate": 4.5386978322177185e-05, "loss": 0.37713539600372314, "step": 882 }, { "epoch": 0.384581881533101, "grad_norm": 1.871374487876892, "learning_rate": 4.5353942459705287e-05, "loss": 0.17814186215400696, "step": 883 }, { "epoch": 0.38501742160278746, "grad_norm": 1.7359042167663574, "learning_rate": 4.532088135153288e-05, "loss": 0.14600001275539398, "step": 884 }, { "epoch": 0.3854529616724739, "grad_norm": 3.2327709197998047, "learning_rate": 4.528779505202065e-05, "loss": 0.41953763365745544, "step": 885 }, { "epoch": 0.3858885017421603, "grad_norm": 2.3193259239196777, "learning_rate": 4.52546836155707e-05, "loss": 0.2808064818382263, "step": 886 }, { "epoch": 0.3863240418118467, "grad_norm": 1.928562045097351, "learning_rate": 4.5221547096626465e-05, "loss": 0.38005247712135315, "step": 887 }, { "epoch": 0.3867595818815331, "grad_norm": 2.336855888366699, "learning_rate": 4.5188385549672634e-05, "loss": 0.3188779056072235, "step": 888 }, { "epoch": 0.3871951219512195, "grad_norm": 2.31748366355896, "learning_rate": 4.515519902923504e-05, "loss": 0.3468675911426544, "step": 889 }, { "epoch": 0.3876306620209059, "grad_norm": 1.5490388870239258, "learning_rate": 4.5121987589880565e-05, "loss": 0.15842217206954956, "step": 890 }, { "epoch": 0.38806620209059234, "grad_norm": 3.5019423961639404, "learning_rate": 4.508875128621707e-05, "loss": 0.28810760378837585, "step": 891 }, { "epoch": 0.3885017421602787, "grad_norm": 2.0126070976257324, "learning_rate": 4.505549017289333e-05, "loss": 0.2353540062904358, "step": 892 }, { "epoch": 0.38893728222996515, "grad_norm": 1.9609909057617188, "learning_rate": 4.502220430459887e-05, "loss": 0.3874630928039551, "step": 893 }, { "epoch": 0.3893728222996516, "grad_norm": 2.0348684787750244, "learning_rate": 4.4988893736063947e-05, "loss": 0.3751717507839203, "step": 894 }, { "epoch": 0.38980836236933797, "grad_norm": 2.0112955570220947, "learning_rate": 4.495555852205941e-05, "loss": 0.40611499547958374, "step": 895 }, { "epoch": 0.3902439024390244, "grad_norm": 1.2058541774749756, "learning_rate": 4.492219871739666e-05, "loss": 0.10419934242963791, "step": 896 }, { "epoch": 0.3906794425087108, "grad_norm": 2.7054202556610107, "learning_rate": 4.488881437692751e-05, "loss": 0.32684460282325745, "step": 897 }, { "epoch": 0.3911149825783972, "grad_norm": 1.5993212461471558, "learning_rate": 4.485540555554409e-05, "loss": 0.18016701936721802, "step": 898 }, { "epoch": 0.3915505226480836, "grad_norm": 2.3083279132843018, "learning_rate": 4.482197230817885e-05, "loss": 0.3840901851654053, "step": 899 }, { "epoch": 0.39198606271777003, "grad_norm": 3.015695571899414, "learning_rate": 4.478851468980435e-05, "loss": 0.4404813349246979, "step": 900 }, { "epoch": 0.39242160278745647, "grad_norm": 2.28902268409729, "learning_rate": 4.475503275543324e-05, "loss": 0.2342604100704193, "step": 901 }, { "epoch": 0.39285714285714285, "grad_norm": 1.9270371198654175, "learning_rate": 4.472152656011814e-05, "loss": 0.1430806964635849, "step": 902 }, { "epoch": 0.3932926829268293, "grad_norm": 1.5050816535949707, "learning_rate": 4.468799615895158e-05, "loss": 0.2087690532207489, "step": 903 }, { "epoch": 0.39372822299651566, "grad_norm": 3.2533674240112305, "learning_rate": 4.465444160706586e-05, "loss": 0.31095901131629944, "step": 904 }, { "epoch": 0.3941637630662021, "grad_norm": 2.875899314880371, "learning_rate": 4.462086295963304e-05, "loss": 0.3637046217918396, "step": 905 }, { "epoch": 0.3945993031358885, "grad_norm": 2.6985037326812744, "learning_rate": 4.458726027186475e-05, "loss": 0.3689204752445221, "step": 906 }, { "epoch": 0.3950348432055749, "grad_norm": 1.9792944192886353, "learning_rate": 4.455363359901216e-05, "loss": 0.2858157157897949, "step": 907 }, { "epoch": 0.39547038327526135, "grad_norm": 290.6600036621094, "learning_rate": 4.4519982996365904e-05, "loss": 2.9012584686279297, "step": 908 }, { "epoch": 0.39590592334494773, "grad_norm": 2.054550886154175, "learning_rate": 4.448630851925593e-05, "loss": 0.1844339221715927, "step": 909 }, { "epoch": 0.39634146341463417, "grad_norm": 1.793392539024353, "learning_rate": 4.445261022305146e-05, "loss": 0.24598374962806702, "step": 910 }, { "epoch": 0.39677700348432055, "grad_norm": 1.6666088104248047, "learning_rate": 4.4418888163160877e-05, "loss": 0.2094908207654953, "step": 911 }, { "epoch": 0.397212543554007, "grad_norm": 2.18825101852417, "learning_rate": 4.438514239503162e-05, "loss": 0.34002190828323364, "step": 912 }, { "epoch": 0.39764808362369336, "grad_norm": 2.982192039489746, "learning_rate": 4.4351372974150136e-05, "loss": 0.3183772563934326, "step": 913 }, { "epoch": 0.3980836236933798, "grad_norm": 2.1596477031707764, "learning_rate": 4.4317579956041764e-05, "loss": 0.21566207706928253, "step": 914 }, { "epoch": 0.3985191637630662, "grad_norm": 1.9461866617202759, "learning_rate": 4.428376339627061e-05, "loss": 0.15616366267204285, "step": 915 }, { "epoch": 0.3989547038327526, "grad_norm": 1.5195719003677368, "learning_rate": 4.4249923350439534e-05, "loss": 0.16720472276210785, "step": 916 }, { "epoch": 0.39939024390243905, "grad_norm": 2.3700497150421143, "learning_rate": 4.421605987418996e-05, "loss": 0.37578192353248596, "step": 917 }, { "epoch": 0.3998257839721254, "grad_norm": 1.9579461812973022, "learning_rate": 4.4182173023201884e-05, "loss": 0.40221208333969116, "step": 918 }, { "epoch": 0.40026132404181186, "grad_norm": 4.54142951965332, "learning_rate": 4.4148262853193724e-05, "loss": 0.4499346613883972, "step": 919 }, { "epoch": 0.40069686411149824, "grad_norm": 3.385910749435425, "learning_rate": 4.411432941992222e-05, "loss": 0.386046826839447, "step": 920 }, { "epoch": 0.4011324041811847, "grad_norm": 2.0574419498443604, "learning_rate": 4.4080372779182385e-05, "loss": 0.37446242570877075, "step": 921 }, { "epoch": 0.40156794425087106, "grad_norm": 2.4433603286743164, "learning_rate": 4.4046392986807374e-05, "loss": 0.3782312273979187, "step": 922 }, { "epoch": 0.4020034843205575, "grad_norm": 1.7931782007217407, "learning_rate": 4.4012390098668434e-05, "loss": 0.2744954526424408, "step": 923 }, { "epoch": 0.4024390243902439, "grad_norm": 2.7063257694244385, "learning_rate": 4.397836417067474e-05, "loss": 0.24188196659088135, "step": 924 }, { "epoch": 0.4028745644599303, "grad_norm": 1.614099144935608, "learning_rate": 4.3944315258773424e-05, "loss": 0.11933901160955429, "step": 925 }, { "epoch": 0.40331010452961674, "grad_norm": 1.8113682270050049, "learning_rate": 4.391024341894933e-05, "loss": 0.2077467441558838, "step": 926 }, { "epoch": 0.4037456445993031, "grad_norm": 2.136359453201294, "learning_rate": 4.3876148707225067e-05, "loss": 0.2716275751590729, "step": 927 }, { "epoch": 0.40418118466898956, "grad_norm": 2.130950450897217, "learning_rate": 4.384203117966079e-05, "loss": 0.3650788366794586, "step": 928 }, { "epoch": 0.40461672473867594, "grad_norm": 1.770280122756958, "learning_rate": 4.380789089235422e-05, "loss": 0.12962089478969574, "step": 929 }, { "epoch": 0.40505226480836237, "grad_norm": 1.9038286209106445, "learning_rate": 4.377372790144049e-05, "loss": 0.20767280459403992, "step": 930 }, { "epoch": 0.4054878048780488, "grad_norm": 2.104893207550049, "learning_rate": 4.373954226309203e-05, "loss": 0.25325140357017517, "step": 931 }, { "epoch": 0.4059233449477352, "grad_norm": 1.9297376871109009, "learning_rate": 4.370533403351855e-05, "loss": 0.23843050003051758, "step": 932 }, { "epoch": 0.4063588850174216, "grad_norm": 2.3137731552124023, "learning_rate": 4.367110326896688e-05, "loss": 0.39864328503608704, "step": 933 }, { "epoch": 0.406794425087108, "grad_norm": 4.147006511688232, "learning_rate": 4.363685002572092e-05, "loss": 0.2789791524410248, "step": 934 }, { "epoch": 0.40722996515679444, "grad_norm": 3.185917377471924, "learning_rate": 4.360257436010152e-05, "loss": 0.16983839869499207, "step": 935 }, { "epoch": 0.4076655052264808, "grad_norm": 2.532496452331543, "learning_rate": 4.3568276328466396e-05, "loss": 0.41707172989845276, "step": 936 }, { "epoch": 0.40810104529616725, "grad_norm": 3.1450369358062744, "learning_rate": 4.353395598721004e-05, "loss": 0.5653339624404907, "step": 937 }, { "epoch": 0.40853658536585363, "grad_norm": 2.3720433712005615, "learning_rate": 4.3499613392763636e-05, "loss": 0.4383832812309265, "step": 938 }, { "epoch": 0.40897212543554007, "grad_norm": 2.2802417278289795, "learning_rate": 4.3465248601594956e-05, "loss": 0.17606112360954285, "step": 939 }, { "epoch": 0.4094076655052265, "grad_norm": 3.1008355617523193, "learning_rate": 4.3430861670208244e-05, "loss": 0.2367875874042511, "step": 940 }, { "epoch": 0.4098432055749129, "grad_norm": 1.8726050853729248, "learning_rate": 4.33964526551442e-05, "loss": 0.25677791237831116, "step": 941 }, { "epoch": 0.4102787456445993, "grad_norm": 1.865566372871399, "learning_rate": 4.336202161297977e-05, "loss": 0.22968684136867523, "step": 942 }, { "epoch": 0.4107142857142857, "grad_norm": 1.5942243337631226, "learning_rate": 4.3327568600328185e-05, "loss": 0.11294664442539215, "step": 943 }, { "epoch": 0.41114982578397213, "grad_norm": 2.3330395221710205, "learning_rate": 4.329309367383874e-05, "loss": 0.4628675878047943, "step": 944 }, { "epoch": 0.4115853658536585, "grad_norm": 2.323913335800171, "learning_rate": 4.3258596890196806e-05, "loss": 0.345470666885376, "step": 945 }, { "epoch": 0.41202090592334495, "grad_norm": 2.159897804260254, "learning_rate": 4.322407830612367e-05, "loss": 0.28461676836013794, "step": 946 }, { "epoch": 0.4124564459930314, "grad_norm": 1.7452759742736816, "learning_rate": 4.318953797837647e-05, "loss": 0.2049267292022705, "step": 947 }, { "epoch": 0.41289198606271776, "grad_norm": 2.6372017860412598, "learning_rate": 4.315497596374809e-05, "loss": 0.4714125692844391, "step": 948 }, { "epoch": 0.4133275261324042, "grad_norm": 1.8999590873718262, "learning_rate": 4.3120392319067085e-05, "loss": 0.2355360984802246, "step": 949 }, { "epoch": 0.4137630662020906, "grad_norm": 1.5243780612945557, "learning_rate": 4.308578710119758e-05, "loss": 0.16119180619716644, "step": 950 }, { "epoch": 0.414198606271777, "grad_norm": 2.480419158935547, "learning_rate": 4.305116036703914e-05, "loss": 0.21980510652065277, "step": 951 }, { "epoch": 0.4146341463414634, "grad_norm": 2.1265127658843994, "learning_rate": 4.3016512173526744e-05, "loss": 0.28115135431289673, "step": 952 }, { "epoch": 0.41506968641114983, "grad_norm": 1.7992740869522095, "learning_rate": 4.298184257763064e-05, "loss": 0.21461021900177002, "step": 953 }, { "epoch": 0.4155052264808362, "grad_norm": 1.6940401792526245, "learning_rate": 4.294715163635626e-05, "loss": 0.17362363636493683, "step": 954 }, { "epoch": 0.41594076655052264, "grad_norm": 2.0729286670684814, "learning_rate": 4.291243940674414e-05, "loss": 0.300682932138443, "step": 955 }, { "epoch": 0.4163763066202091, "grad_norm": 1.8306151628494263, "learning_rate": 4.2877705945869825e-05, "loss": 0.24257077276706696, "step": 956 }, { "epoch": 0.41681184668989546, "grad_norm": 2.0635182857513428, "learning_rate": 4.2842951310843774e-05, "loss": 0.11749780923128128, "step": 957 }, { "epoch": 0.4172473867595819, "grad_norm": 1.8503384590148926, "learning_rate": 4.280817555881122e-05, "loss": 0.4075123071670532, "step": 958 }, { "epoch": 0.4176829268292683, "grad_norm": 1.8040497303009033, "learning_rate": 4.277337874695218e-05, "loss": 0.2563296854496002, "step": 959 }, { "epoch": 0.4181184668989547, "grad_norm": 2.5588722229003906, "learning_rate": 4.273856093248126e-05, "loss": 0.48061805963516235, "step": 960 }, { "epoch": 0.4185540069686411, "grad_norm": 2.956188440322876, "learning_rate": 4.2703722172647604e-05, "loss": 0.2670336663722992, "step": 961 }, { "epoch": 0.4189895470383275, "grad_norm": 2.2303805351257324, "learning_rate": 4.26688625247348e-05, "loss": 0.32827040553092957, "step": 962 }, { "epoch": 0.41942508710801396, "grad_norm": 1.871222734451294, "learning_rate": 4.2633982046060774e-05, "loss": 0.23880444467067719, "step": 963 }, { "epoch": 0.41986062717770034, "grad_norm": 1.8872041702270508, "learning_rate": 4.259908079397772e-05, "loss": 0.29812219738960266, "step": 964 }, { "epoch": 0.4202961672473868, "grad_norm": 1.8570531606674194, "learning_rate": 4.256415882587198e-05, "loss": 0.22244131565093994, "step": 965 }, { "epoch": 0.42073170731707316, "grad_norm": 1.3347151279449463, "learning_rate": 4.252921619916393e-05, "loss": 0.11683449894189835, "step": 966 }, { "epoch": 0.4211672473867596, "grad_norm": 2.401367425918579, "learning_rate": 4.2494252971307974e-05, "loss": 0.35306575894355774, "step": 967 }, { "epoch": 0.42160278745644597, "grad_norm": 1.8394988775253296, "learning_rate": 4.245926919979235e-05, "loss": 0.19184793531894684, "step": 968 }, { "epoch": 0.4220383275261324, "grad_norm": 2.1858699321746826, "learning_rate": 4.242426494213905e-05, "loss": 0.24983565509319305, "step": 969 }, { "epoch": 0.42247386759581884, "grad_norm": 1.3739334344863892, "learning_rate": 4.23892402559038e-05, "loss": 0.09930071979761124, "step": 970 }, { "epoch": 0.4229094076655052, "grad_norm": 1.7197543382644653, "learning_rate": 4.235419519867591e-05, "loss": 0.22170346975326538, "step": 971 }, { "epoch": 0.42334494773519166, "grad_norm": 2.004143476486206, "learning_rate": 4.2319129828078144e-05, "loss": 0.24919940531253815, "step": 972 }, { "epoch": 0.42378048780487804, "grad_norm": 1.678539514541626, "learning_rate": 4.228404420176672e-05, "loss": 0.2413455992937088, "step": 973 }, { "epoch": 0.42421602787456447, "grad_norm": 2.67918062210083, "learning_rate": 4.224893837743112e-05, "loss": 0.32433634996414185, "step": 974 }, { "epoch": 0.42465156794425085, "grad_norm": 2.4954192638397217, "learning_rate": 4.221381241279404e-05, "loss": 0.22011467814445496, "step": 975 }, { "epoch": 0.4250871080139373, "grad_norm": 2.9000563621520996, "learning_rate": 4.2178666365611326e-05, "loss": 0.253103107213974, "step": 976 }, { "epoch": 0.42552264808362367, "grad_norm": 1.63368558883667, "learning_rate": 4.214350029367181e-05, "loss": 0.1841430813074112, "step": 977 }, { "epoch": 0.4259581881533101, "grad_norm": 1.8548649549484253, "learning_rate": 4.210831425479727e-05, "loss": 0.1870099902153015, "step": 978 }, { "epoch": 0.42639372822299654, "grad_norm": 2.1839723587036133, "learning_rate": 4.2073108306842304e-05, "loss": 0.4274691939353943, "step": 979 }, { "epoch": 0.4268292682926829, "grad_norm": 2.029909372329712, "learning_rate": 4.203788250769423e-05, "loss": 0.2532752752304077, "step": 980 }, { "epoch": 0.42726480836236935, "grad_norm": 1.8807498216629028, "learning_rate": 4.200263691527304e-05, "loss": 0.2725544273853302, "step": 981 }, { "epoch": 0.42770034843205573, "grad_norm": 1.6516238451004028, "learning_rate": 4.196737158753125e-05, "loss": 0.23303918540477753, "step": 982 }, { "epoch": 0.42813588850174217, "grad_norm": 2.0873897075653076, "learning_rate": 4.193208658245384e-05, "loss": 0.23010580241680145, "step": 983 }, { "epoch": 0.42857142857142855, "grad_norm": 1.4161659479141235, "learning_rate": 4.189678195805812e-05, "loss": 0.13613292574882507, "step": 984 }, { "epoch": 0.429006968641115, "grad_norm": 2.082766532897949, "learning_rate": 4.186145777239368e-05, "loss": 0.37587469816207886, "step": 985 }, { "epoch": 0.4294425087108014, "grad_norm": 1.2092549800872803, "learning_rate": 4.182611408354227e-05, "loss": 0.07028897851705551, "step": 986 }, { "epoch": 0.4298780487804878, "grad_norm": 1.6855392456054688, "learning_rate": 4.1790750949617714e-05, "loss": 0.17492924630641937, "step": 987 }, { "epoch": 0.43031358885017423, "grad_norm": 1.2352831363677979, "learning_rate": 4.175536842876578e-05, "loss": 0.08578023314476013, "step": 988 }, { "epoch": 0.4307491289198606, "grad_norm": 1.5761475563049316, "learning_rate": 4.171996657916415e-05, "loss": 0.22124648094177246, "step": 989 }, { "epoch": 0.43118466898954705, "grad_norm": 1.6022588014602661, "learning_rate": 4.1684545459022265e-05, "loss": 0.1353543996810913, "step": 990 }, { "epoch": 0.43162020905923343, "grad_norm": 1.757262110710144, "learning_rate": 4.1649105126581255e-05, "loss": 0.2399410754442215, "step": 991 }, { "epoch": 0.43205574912891986, "grad_norm": 1.6773788928985596, "learning_rate": 4.1613645640113844e-05, "loss": 0.18033163249492645, "step": 992 }, { "epoch": 0.4324912891986063, "grad_norm": 1.519549012184143, "learning_rate": 4.157816705792425e-05, "loss": 0.16516245901584625, "step": 993 }, { "epoch": 0.4329268292682927, "grad_norm": 2.4569895267486572, "learning_rate": 4.154266943834808e-05, "loss": 0.5264909267425537, "step": 994 }, { "epoch": 0.4333623693379791, "grad_norm": 1.8953137397766113, "learning_rate": 4.150715283975226e-05, "loss": 0.2877585291862488, "step": 995 }, { "epoch": 0.4337979094076655, "grad_norm": 5.475688934326172, "learning_rate": 4.147161732053491e-05, "loss": 0.2908034920692444, "step": 996 }, { "epoch": 0.43423344947735193, "grad_norm": 2.009016990661621, "learning_rate": 4.143606293912525e-05, "loss": 0.29379820823669434, "step": 997 }, { "epoch": 0.4346689895470383, "grad_norm": 2.2312984466552734, "learning_rate": 4.1400489753983547e-05, "loss": 0.3389362096786499, "step": 998 }, { "epoch": 0.43510452961672474, "grad_norm": 2.484955072402954, "learning_rate": 4.1364897823600946e-05, "loss": 0.2630944848060608, "step": 999 }, { "epoch": 0.4355400696864111, "grad_norm": 2.4746384620666504, "learning_rate": 4.132928720649945e-05, "loss": 0.23273994028568268, "step": 1000 }, { "epoch": 0.43597560975609756, "grad_norm": 2.8906540870666504, "learning_rate": 4.129365796123176e-05, "loss": 0.24152767658233643, "step": 1001 }, { "epoch": 0.436411149825784, "grad_norm": 2.3826897144317627, "learning_rate": 4.125801014638123e-05, "loss": 0.4553738832473755, "step": 1002 }, { "epoch": 0.4368466898954704, "grad_norm": 1.6368283033370972, "learning_rate": 4.122234382056172e-05, "loss": 0.21736015379428864, "step": 1003 }, { "epoch": 0.4372822299651568, "grad_norm": 1.78972327709198, "learning_rate": 4.1186659042417544e-05, "loss": 0.1785997748374939, "step": 1004 }, { "epoch": 0.4377177700348432, "grad_norm": 1.8462789058685303, "learning_rate": 4.115095587062336e-05, "loss": 0.19652527570724487, "step": 1005 }, { "epoch": 0.4381533101045296, "grad_norm": 1.4874708652496338, "learning_rate": 4.111523436388407e-05, "loss": 0.16495780646800995, "step": 1006 }, { "epoch": 0.438588850174216, "grad_norm": 1.185657262802124, "learning_rate": 4.1079494580934696e-05, "loss": 0.07202600687742233, "step": 1007 }, { "epoch": 0.43902439024390244, "grad_norm": 1.9535876512527466, "learning_rate": 4.104373658054034e-05, "loss": 0.2809737026691437, "step": 1008 }, { "epoch": 0.4394599303135889, "grad_norm": 2.17014217376709, "learning_rate": 4.100796042149605e-05, "loss": 0.31771209836006165, "step": 1009 }, { "epoch": 0.43989547038327526, "grad_norm": 2.2775838375091553, "learning_rate": 4.0972166162626735e-05, "loss": 0.30792367458343506, "step": 1010 }, { "epoch": 0.4403310104529617, "grad_norm": 2.6030287742614746, "learning_rate": 4.0936353862787064e-05, "loss": 0.6439055800437927, "step": 1011 }, { "epoch": 0.44076655052264807, "grad_norm": 2.1043639183044434, "learning_rate": 4.090052358086134e-05, "loss": 0.26491498947143555, "step": 1012 }, { "epoch": 0.4412020905923345, "grad_norm": 4.263086795806885, "learning_rate": 4.08646753757635e-05, "loss": 0.22857271134853363, "step": 1013 }, { "epoch": 0.4416376306620209, "grad_norm": 1.7173675298690796, "learning_rate": 4.082880930643687e-05, "loss": 0.1753542423248291, "step": 1014 }, { "epoch": 0.4420731707317073, "grad_norm": 1.4423112869262695, "learning_rate": 4.0792925431854214e-05, "loss": 0.17598173022270203, "step": 1015 }, { "epoch": 0.4425087108013937, "grad_norm": 2.5329623222351074, "learning_rate": 4.0757023811017526e-05, "loss": 0.2128322869539261, "step": 1016 }, { "epoch": 0.44294425087108014, "grad_norm": 2.226210594177246, "learning_rate": 4.072110450295803e-05, "loss": 0.1874837726354599, "step": 1017 }, { "epoch": 0.44337979094076657, "grad_norm": 1.9166638851165771, "learning_rate": 4.068516756673598e-05, "loss": 0.2177751660346985, "step": 1018 }, { "epoch": 0.44381533101045295, "grad_norm": 10.40202808380127, "learning_rate": 4.0649213061440645e-05, "loss": 0.3713855743408203, "step": 1019 }, { "epoch": 0.4442508710801394, "grad_norm": 2.716055154800415, "learning_rate": 4.0613241046190175e-05, "loss": 0.36425653100013733, "step": 1020 }, { "epoch": 0.44468641114982577, "grad_norm": 2.1875741481781006, "learning_rate": 4.0577251580131505e-05, "loss": 0.29257893562316895, "step": 1021 }, { "epoch": 0.4451219512195122, "grad_norm": 3.214385747909546, "learning_rate": 4.054124472244029e-05, "loss": 0.4335079491138458, "step": 1022 }, { "epoch": 0.4455574912891986, "grad_norm": 2.326630115509033, "learning_rate": 4.050522053232073e-05, "loss": 0.34904661774635315, "step": 1023 }, { "epoch": 0.445993031358885, "grad_norm": 1.6926970481872559, "learning_rate": 4.046917906900557e-05, "loss": 0.2000325471162796, "step": 1024 }, { "epoch": 0.44642857142857145, "grad_norm": 2.481614112854004, "learning_rate": 4.0433120391755956e-05, "loss": 0.2251674383878708, "step": 1025 }, { "epoch": 0.44686411149825783, "grad_norm": 2.767874002456665, "learning_rate": 4.039704455986129e-05, "loss": 0.166401669383049, "step": 1026 }, { "epoch": 0.44729965156794427, "grad_norm": 2.0968570709228516, "learning_rate": 4.0360951632639226e-05, "loss": 0.2338012456893921, "step": 1027 }, { "epoch": 0.44773519163763065, "grad_norm": 1.6682534217834473, "learning_rate": 4.032484166943553e-05, "loss": 0.16686654090881348, "step": 1028 }, { "epoch": 0.4481707317073171, "grad_norm": 1.7409390211105347, "learning_rate": 4.0288714729623946e-05, "loss": 0.20249372720718384, "step": 1029 }, { "epoch": 0.44860627177700346, "grad_norm": 1.755963683128357, "learning_rate": 4.025257087260616e-05, "loss": 0.1978229582309723, "step": 1030 }, { "epoch": 0.4490418118466899, "grad_norm": 2.0796258449554443, "learning_rate": 4.021641015781165e-05, "loss": 0.27793261408805847, "step": 1031 }, { "epoch": 0.44947735191637633, "grad_norm": 0.9890313744544983, "learning_rate": 4.018023264469763e-05, "loss": 0.08678162097930908, "step": 1032 }, { "epoch": 0.4499128919860627, "grad_norm": 1.8974298238754272, "learning_rate": 4.014403839274894e-05, "loss": 0.24924422800540924, "step": 1033 }, { "epoch": 0.45034843205574915, "grad_norm": 3.0077805519104004, "learning_rate": 4.0107827461477925e-05, "loss": 0.3869110941886902, "step": 1034 }, { "epoch": 0.45078397212543553, "grad_norm": 2.050006628036499, "learning_rate": 4.0071599910424366e-05, "loss": 0.23416951298713684, "step": 1035 }, { "epoch": 0.45121951219512196, "grad_norm": 2.593156337738037, "learning_rate": 4.003535579915537e-05, "loss": 0.3253931999206543, "step": 1036 }, { "epoch": 0.45165505226480834, "grad_norm": 1.6890918016433716, "learning_rate": 3.999909518726526e-05, "loss": 0.1908685564994812, "step": 1037 }, { "epoch": 0.4520905923344948, "grad_norm": 2.0124287605285645, "learning_rate": 3.996281813437551e-05, "loss": 0.22000683844089508, "step": 1038 }, { "epoch": 0.45252613240418116, "grad_norm": 1.9493992328643799, "learning_rate": 3.9926524700134615e-05, "loss": 0.23390452563762665, "step": 1039 }, { "epoch": 0.4529616724738676, "grad_norm": 1.9060395956039429, "learning_rate": 3.9890214944218016e-05, "loss": 0.19219157099723816, "step": 1040 }, { "epoch": 0.45339721254355403, "grad_norm": 1.98427414894104, "learning_rate": 3.985388892632797e-05, "loss": 0.24846132099628448, "step": 1041 }, { "epoch": 0.4538327526132404, "grad_norm": 2.42861008644104, "learning_rate": 3.981754670619351e-05, "loss": 0.31060081720352173, "step": 1042 }, { "epoch": 0.45426829268292684, "grad_norm": 1.6326144933700562, "learning_rate": 3.9781188343570257e-05, "loss": 0.10890248417854309, "step": 1043 }, { "epoch": 0.4547038327526132, "grad_norm": 1.8023030757904053, "learning_rate": 3.974481389824043e-05, "loss": 0.2299550622701645, "step": 1044 }, { "epoch": 0.45513937282229966, "grad_norm": 2.3280529975891113, "learning_rate": 3.9708423430012624e-05, "loss": 0.2716372013092041, "step": 1045 }, { "epoch": 0.45557491289198604, "grad_norm": 1.5614609718322754, "learning_rate": 3.967201699872187e-05, "loss": 0.17763203382492065, "step": 1046 }, { "epoch": 0.4560104529616725, "grad_norm": 2.5043132305145264, "learning_rate": 3.9635594664229374e-05, "loss": 0.3421574532985687, "step": 1047 }, { "epoch": 0.4564459930313589, "grad_norm": 1.4411299228668213, "learning_rate": 3.9599156486422505e-05, "loss": 0.1556592881679535, "step": 1048 }, { "epoch": 0.4568815331010453, "grad_norm": 2.5077855587005615, "learning_rate": 3.95627025252147e-05, "loss": 0.5266510248184204, "step": 1049 }, { "epoch": 0.4573170731707317, "grad_norm": 1.9919426441192627, "learning_rate": 3.9526232840545334e-05, "loss": 0.2659042179584503, "step": 1050 }, { "epoch": 0.4577526132404181, "grad_norm": 2.2780230045318604, "learning_rate": 3.948974749237964e-05, "loss": 0.36428526043891907, "step": 1051 }, { "epoch": 0.45818815331010454, "grad_norm": 2.3657538890838623, "learning_rate": 3.945324654070863e-05, "loss": 0.4230879247188568, "step": 1052 }, { "epoch": 0.4586236933797909, "grad_norm": 1.126559853553772, "learning_rate": 3.941673004554891e-05, "loss": 0.1057363748550415, "step": 1053 }, { "epoch": 0.45905923344947736, "grad_norm": 2.1077284812927246, "learning_rate": 3.93801980669427e-05, "loss": 0.4350264072418213, "step": 1054 }, { "epoch": 0.4594947735191638, "grad_norm": 2.2297935485839844, "learning_rate": 3.9343650664957656e-05, "loss": 0.3553493618965149, "step": 1055 }, { "epoch": 0.45993031358885017, "grad_norm": 2.1402523517608643, "learning_rate": 3.9307087899686805e-05, "loss": 0.30047255754470825, "step": 1056 }, { "epoch": 0.4603658536585366, "grad_norm": 2.0212974548339844, "learning_rate": 3.927050983124842e-05, "loss": 0.20427030324935913, "step": 1057 }, { "epoch": 0.460801393728223, "grad_norm": 1.7246992588043213, "learning_rate": 3.923391651978595e-05, "loss": 0.281399130821228, "step": 1058 }, { "epoch": 0.4612369337979094, "grad_norm": 1.9288454055786133, "learning_rate": 3.91973080254679e-05, "loss": 0.14276517927646637, "step": 1059 }, { "epoch": 0.4616724738675958, "grad_norm": 2.8457846641540527, "learning_rate": 3.916068440848773e-05, "loss": 0.26192185282707214, "step": 1060 }, { "epoch": 0.46210801393728224, "grad_norm": 1.8432071208953857, "learning_rate": 3.9124045729063785e-05, "loss": 0.34318462014198303, "step": 1061 }, { "epoch": 0.4625435540069686, "grad_norm": 2.0565929412841797, "learning_rate": 3.9087392047439164e-05, "loss": 0.397199422121048, "step": 1062 }, { "epoch": 0.46297909407665505, "grad_norm": 2.4439921379089355, "learning_rate": 3.905072342388165e-05, "loss": 0.30207327008247375, "step": 1063 }, { "epoch": 0.4634146341463415, "grad_norm": 2.050793170928955, "learning_rate": 3.901403991868356e-05, "loss": 0.16369059681892395, "step": 1064 }, { "epoch": 0.46385017421602787, "grad_norm": 2.0417544841766357, "learning_rate": 3.897734159216171e-05, "loss": 0.2773264944553375, "step": 1065 }, { "epoch": 0.4642857142857143, "grad_norm": 1.908002257347107, "learning_rate": 3.894062850465728e-05, "loss": 0.2917279005050659, "step": 1066 }, { "epoch": 0.4647212543554007, "grad_norm": 1.4750418663024902, "learning_rate": 3.8903900716535716e-05, "loss": 0.17489050328731537, "step": 1067 }, { "epoch": 0.4651567944250871, "grad_norm": 1.8329523801803589, "learning_rate": 3.886715828818664e-05, "loss": 0.18389306962490082, "step": 1068 }, { "epoch": 0.4655923344947735, "grad_norm": 4.052893161773682, "learning_rate": 3.8830401280023735e-05, "loss": 0.1971951723098755, "step": 1069 }, { "epoch": 0.46602787456445993, "grad_norm": 1.2665988206863403, "learning_rate": 3.8793629752484683e-05, "loss": 0.1589955985546112, "step": 1070 }, { "epoch": 0.46646341463414637, "grad_norm": 1.4124928712844849, "learning_rate": 3.875684376603101e-05, "loss": 0.1795637160539627, "step": 1071 }, { "epoch": 0.46689895470383275, "grad_norm": 1.530629277229309, "learning_rate": 3.8720043381148014e-05, "loss": 0.20030775666236877, "step": 1072 }, { "epoch": 0.4673344947735192, "grad_norm": 2.1725456714630127, "learning_rate": 3.8683228658344695e-05, "loss": 0.4135640561580658, "step": 1073 }, { "epoch": 0.46777003484320556, "grad_norm": 1.5520142316818237, "learning_rate": 3.864639965815362e-05, "loss": 0.1797064244747162, "step": 1074 }, { "epoch": 0.468205574912892, "grad_norm": 1.2044910192489624, "learning_rate": 3.860955644113082e-05, "loss": 0.119352325797081, "step": 1075 }, { "epoch": 0.4686411149825784, "grad_norm": 1.670790195465088, "learning_rate": 3.857269906785571e-05, "loss": 0.23476135730743408, "step": 1076 }, { "epoch": 0.4690766550522648, "grad_norm": 1.4100192785263062, "learning_rate": 3.853582759893097e-05, "loss": 0.16152602434158325, "step": 1077 }, { "epoch": 0.4695121951219512, "grad_norm": 1.6012604236602783, "learning_rate": 3.849894209498249e-05, "loss": 0.19146762788295746, "step": 1078 }, { "epoch": 0.46994773519163763, "grad_norm": 2.1748833656311035, "learning_rate": 3.846204261665918e-05, "loss": 0.32349032163619995, "step": 1079 }, { "epoch": 0.47038327526132406, "grad_norm": 1.5371596813201904, "learning_rate": 3.842512922463299e-05, "loss": 0.10898125916719437, "step": 1080 }, { "epoch": 0.47081881533101044, "grad_norm": 1.8772963285446167, "learning_rate": 3.83882019795987e-05, "loss": 0.2286071628332138, "step": 1081 }, { "epoch": 0.4712543554006969, "grad_norm": 1.8666821718215942, "learning_rate": 3.8351260942273905e-05, "loss": 0.29231593012809753, "step": 1082 }, { "epoch": 0.47168989547038326, "grad_norm": 1.6794028282165527, "learning_rate": 3.8314306173398835e-05, "loss": 0.2852476239204407, "step": 1083 }, { "epoch": 0.4721254355400697, "grad_norm": 1.8610312938690186, "learning_rate": 3.8277337733736336e-05, "loss": 0.21379250288009644, "step": 1084 }, { "epoch": 0.4725609756097561, "grad_norm": 3.9601831436157227, "learning_rate": 3.824035568407171e-05, "loss": 0.26303401589393616, "step": 1085 }, { "epoch": 0.4729965156794425, "grad_norm": 2.074098825454712, "learning_rate": 3.820336008521266e-05, "loss": 0.3794580101966858, "step": 1086 }, { "epoch": 0.47343205574912894, "grad_norm": 2.3670401573181152, "learning_rate": 3.816635099798914e-05, "loss": 0.45137739181518555, "step": 1087 }, { "epoch": 0.4738675958188153, "grad_norm": 2.1595757007598877, "learning_rate": 3.8129328483253294e-05, "loss": 0.20874722301959991, "step": 1088 }, { "epoch": 0.47430313588850176, "grad_norm": 8.217854499816895, "learning_rate": 3.809229260187935e-05, "loss": 0.3662978410720825, "step": 1089 }, { "epoch": 0.47473867595818814, "grad_norm": 4.416383743286133, "learning_rate": 3.805524341476352e-05, "loss": 0.20218460261821747, "step": 1090 }, { "epoch": 0.4751742160278746, "grad_norm": 2.4727258682250977, "learning_rate": 3.801818098282386e-05, "loss": 0.31493085622787476, "step": 1091 }, { "epoch": 0.47560975609756095, "grad_norm": 1.5364067554473877, "learning_rate": 3.7981105367000255e-05, "loss": 0.21770140528678894, "step": 1092 }, { "epoch": 0.4760452961672474, "grad_norm": 1.3883204460144043, "learning_rate": 3.794401662825422e-05, "loss": 0.07463032007217407, "step": 1093 }, { "epoch": 0.4764808362369338, "grad_norm": 2.752943992614746, "learning_rate": 3.790691482756886e-05, "loss": 0.1984841525554657, "step": 1094 }, { "epoch": 0.4769163763066202, "grad_norm": 2.1443254947662354, "learning_rate": 3.786980002594879e-05, "loss": 0.3150251507759094, "step": 1095 }, { "epoch": 0.47735191637630664, "grad_norm": 1.4597605466842651, "learning_rate": 3.7832672284419946e-05, "loss": 0.14665824174880981, "step": 1096 }, { "epoch": 0.477787456445993, "grad_norm": 1.60385262966156, "learning_rate": 3.779553166402959e-05, "loss": 0.12216822057962418, "step": 1097 }, { "epoch": 0.47822299651567945, "grad_norm": 1.6355791091918945, "learning_rate": 3.775837822584614e-05, "loss": 0.2450210452079773, "step": 1098 }, { "epoch": 0.47865853658536583, "grad_norm": 1.816836953163147, "learning_rate": 3.7721212030959075e-05, "loss": 0.26053452491760254, "step": 1099 }, { "epoch": 0.47909407665505227, "grad_norm": 2.1515588760375977, "learning_rate": 3.768403314047888e-05, "loss": 0.23760691285133362, "step": 1100 }, { "epoch": 0.47952961672473865, "grad_norm": 2.116184711456299, "learning_rate": 3.764684161553688e-05, "loss": 0.4242888391017914, "step": 1101 }, { "epoch": 0.4799651567944251, "grad_norm": 1.9052082300186157, "learning_rate": 3.760963751728522e-05, "loss": 0.23510190844535828, "step": 1102 }, { "epoch": 0.4804006968641115, "grad_norm": 2.223618268966675, "learning_rate": 3.7572420906896677e-05, "loss": 0.27720868587493896, "step": 1103 }, { "epoch": 0.4808362369337979, "grad_norm": 2.4222936630249023, "learning_rate": 3.7535191845564614e-05, "loss": 0.3049902617931366, "step": 1104 }, { "epoch": 0.48127177700348434, "grad_norm": 2.2711338996887207, "learning_rate": 3.749795039450287e-05, "loss": 0.3518047034740448, "step": 1105 }, { "epoch": 0.4817073170731707, "grad_norm": 2.168548107147217, "learning_rate": 3.7460696614945656e-05, "loss": 0.2788136303424835, "step": 1106 }, { "epoch": 0.48214285714285715, "grad_norm": 1.606977105140686, "learning_rate": 3.742343056814743e-05, "loss": 0.14667417109012604, "step": 1107 }, { "epoch": 0.48257839721254353, "grad_norm": 1.7878289222717285, "learning_rate": 3.738615231538288e-05, "loss": 0.25555139780044556, "step": 1108 }, { "epoch": 0.48301393728222997, "grad_norm": 1.7126524448394775, "learning_rate": 3.7348861917946706e-05, "loss": 0.27080005407333374, "step": 1109 }, { "epoch": 0.4834494773519164, "grad_norm": 1.978907585144043, "learning_rate": 3.73115594371536e-05, "loss": 0.31338369846343994, "step": 1110 }, { "epoch": 0.4838850174216028, "grad_norm": 1.6885507106781006, "learning_rate": 3.727424493433812e-05, "loss": 0.23299245536327362, "step": 1111 }, { "epoch": 0.4843205574912892, "grad_norm": 1.7485069036483765, "learning_rate": 3.7236918470854575e-05, "loss": 0.13693390786647797, "step": 1112 }, { "epoch": 0.4847560975609756, "grad_norm": 1.826476812362671, "learning_rate": 3.719958010807697e-05, "loss": 0.1849220097064972, "step": 1113 }, { "epoch": 0.48519163763066203, "grad_norm": 5.854074954986572, "learning_rate": 3.716222990739888e-05, "loss": 0.09990092366933823, "step": 1114 }, { "epoch": 0.4856271777003484, "grad_norm": 2.0516929626464844, "learning_rate": 3.712486793023329e-05, "loss": 0.3089669346809387, "step": 1115 }, { "epoch": 0.48606271777003485, "grad_norm": 1.940704584121704, "learning_rate": 3.7087494238012596e-05, "loss": 0.23908154666423798, "step": 1116 }, { "epoch": 0.4864982578397213, "grad_norm": 2.3100922107696533, "learning_rate": 3.705010889218846e-05, "loss": 0.31568342447280884, "step": 1117 }, { "epoch": 0.48693379790940766, "grad_norm": 1.7474900484085083, "learning_rate": 3.7012711954231664e-05, "loss": 0.22894521057605743, "step": 1118 }, { "epoch": 0.4873693379790941, "grad_norm": 1.4813580513000488, "learning_rate": 3.697530348563209e-05, "loss": 0.20368552207946777, "step": 1119 }, { "epoch": 0.4878048780487805, "grad_norm": 3.280672311782837, "learning_rate": 3.693788354789857e-05, "loss": 0.43283942341804504, "step": 1120 }, { "epoch": 0.4882404181184669, "grad_norm": 2.5738935470581055, "learning_rate": 3.6900452202558773e-05, "loss": 0.4143170714378357, "step": 1121 }, { "epoch": 0.4886759581881533, "grad_norm": 1.6483888626098633, "learning_rate": 3.686300951115916e-05, "loss": 0.2075437605381012, "step": 1122 }, { "epoch": 0.4891114982578397, "grad_norm": 1.8468018770217896, "learning_rate": 3.682555553526482e-05, "loss": 0.19734838604927063, "step": 1123 }, { "epoch": 0.4895470383275261, "grad_norm": 2.5180857181549072, "learning_rate": 3.67880903364594e-05, "loss": 0.3383256494998932, "step": 1124 }, { "epoch": 0.48998257839721254, "grad_norm": 2.1052417755126953, "learning_rate": 3.6750613976345024e-05, "loss": 0.16855601966381073, "step": 1125 }, { "epoch": 0.490418118466899, "grad_norm": 1.2968577146530151, "learning_rate": 3.671312651654212e-05, "loss": 0.09480296075344086, "step": 1126 }, { "epoch": 0.49085365853658536, "grad_norm": 2.1694722175598145, "learning_rate": 3.667562801868943e-05, "loss": 0.2736762464046478, "step": 1127 }, { "epoch": 0.4912891986062718, "grad_norm": 2.292961597442627, "learning_rate": 3.6638118544443796e-05, "loss": 0.39153796434402466, "step": 1128 }, { "epoch": 0.4917247386759582, "grad_norm": 1.430195927619934, "learning_rate": 3.660059815548012e-05, "loss": 0.15875433385372162, "step": 1129 }, { "epoch": 0.4921602787456446, "grad_norm": 2.2262954711914062, "learning_rate": 3.656306691349126e-05, "loss": 0.5231969356536865, "step": 1130 }, { "epoch": 0.492595818815331, "grad_norm": 1.8816285133361816, "learning_rate": 3.652552488018791e-05, "loss": 0.2707490921020508, "step": 1131 }, { "epoch": 0.4930313588850174, "grad_norm": 2.232910633087158, "learning_rate": 3.64879721172985e-05, "loss": 0.39035457372665405, "step": 1132 }, { "epoch": 0.49346689895470386, "grad_norm": 3.149932622909546, "learning_rate": 3.645040868656914e-05, "loss": 0.4072360396385193, "step": 1133 }, { "epoch": 0.49390243902439024, "grad_norm": 1.986310601234436, "learning_rate": 3.641283464976344e-05, "loss": 0.310905784368515, "step": 1134 }, { "epoch": 0.4943379790940767, "grad_norm": 1.630486011505127, "learning_rate": 3.637525006866245e-05, "loss": 0.1954832822084427, "step": 1135 }, { "epoch": 0.49477351916376305, "grad_norm": 1.542914628982544, "learning_rate": 3.633765500506459e-05, "loss": 0.21935656666755676, "step": 1136 }, { "epoch": 0.4952090592334495, "grad_norm": 0.9337291717529297, "learning_rate": 3.630004952078548e-05, "loss": 0.05458977445960045, "step": 1137 }, { "epoch": 0.49564459930313587, "grad_norm": 1.5782147645950317, "learning_rate": 3.6262433677657905e-05, "loss": 0.15672199428081512, "step": 1138 }, { "epoch": 0.4960801393728223, "grad_norm": 3.4689111709594727, "learning_rate": 3.622480753753166e-05, "loss": 0.34506598114967346, "step": 1139 }, { "epoch": 0.4965156794425087, "grad_norm": 1.7527915239334106, "learning_rate": 3.618717116227347e-05, "loss": 0.2832348644733429, "step": 1140 }, { "epoch": 0.4969512195121951, "grad_norm": 2.610633373260498, "learning_rate": 3.614952461376692e-05, "loss": 0.31143471598625183, "step": 1141 }, { "epoch": 0.49738675958188155, "grad_norm": 1.6302624940872192, "learning_rate": 3.611186795391227e-05, "loss": 0.1804867684841156, "step": 1142 }, { "epoch": 0.49782229965156793, "grad_norm": 2.661018133163452, "learning_rate": 3.607420124462645e-05, "loss": 0.45085033774375916, "step": 1143 }, { "epoch": 0.49825783972125437, "grad_norm": 1.8829233646392822, "learning_rate": 3.603652454784291e-05, "loss": 0.25015872716903687, "step": 1144 }, { "epoch": 0.49869337979094075, "grad_norm": 1.3712189197540283, "learning_rate": 3.5998837925511505e-05, "loss": 0.11537285894155502, "step": 1145 }, { "epoch": 0.4991289198606272, "grad_norm": 2.282701015472412, "learning_rate": 3.59611414395984e-05, "loss": 0.3380337655544281, "step": 1146 }, { "epoch": 0.49956445993031356, "grad_norm": 2.2574007511138916, "learning_rate": 3.592343515208601e-05, "loss": 0.16830267012119293, "step": 1147 }, { "epoch": 0.5, "grad_norm": 2.0298690795898438, "learning_rate": 3.5885719124972853e-05, "loss": 0.2698993980884552, "step": 1148 }, { "epoch": 0.5004355400696864, "grad_norm": 4.269159317016602, "learning_rate": 3.5847993420273456e-05, "loss": 0.388205885887146, "step": 1149 }, { "epoch": 0.5008710801393729, "grad_norm": 1.408455729484558, "learning_rate": 3.581025810001826e-05, "loss": 0.22693203389644623, "step": 1150 }, { "epoch": 0.5013066202090593, "grad_norm": 2.306385040283203, "learning_rate": 3.5772513226253504e-05, "loss": 0.44473230838775635, "step": 1151 }, { "epoch": 0.5017421602787456, "grad_norm": 2.6218597888946533, "learning_rate": 3.573475886104117e-05, "loss": 0.22028397023677826, "step": 1152 }, { "epoch": 0.502177700348432, "grad_norm": 2.36444354057312, "learning_rate": 3.5696995066458815e-05, "loss": 0.2536901831626892, "step": 1153 }, { "epoch": 0.5026132404181185, "grad_norm": 2.2865681648254395, "learning_rate": 3.565922190459951e-05, "loss": 0.3871194124221802, "step": 1154 }, { "epoch": 0.5030487804878049, "grad_norm": 2.7124545574188232, "learning_rate": 3.562143943757174e-05, "loss": 0.4441030025482178, "step": 1155 }, { "epoch": 0.5034843205574913, "grad_norm": 1.7426185607910156, "learning_rate": 3.558364772749926e-05, "loss": 0.1774807572364807, "step": 1156 }, { "epoch": 0.5039198606271778, "grad_norm": 2.0493288040161133, "learning_rate": 3.5545846836521065e-05, "loss": 0.273227721452713, "step": 1157 }, { "epoch": 0.5043554006968641, "grad_norm": 1.5088497400283813, "learning_rate": 3.5508036826791196e-05, "loss": 0.18878690898418427, "step": 1158 }, { "epoch": 0.5047909407665505, "grad_norm": 1.7294305562973022, "learning_rate": 3.547021776047873e-05, "loss": 0.257981538772583, "step": 1159 }, { "epoch": 0.5052264808362369, "grad_norm": 1.827804684638977, "learning_rate": 3.5432389699767616e-05, "loss": 0.12571388483047485, "step": 1160 }, { "epoch": 0.5056620209059234, "grad_norm": 1.653143048286438, "learning_rate": 3.53945527068566e-05, "loss": 0.10509958118200302, "step": 1161 }, { "epoch": 0.5060975609756098, "grad_norm": 1.5076053142547607, "learning_rate": 3.53567068439591e-05, "loss": 0.20317985117435455, "step": 1162 }, { "epoch": 0.5065331010452961, "grad_norm": 2.545489549636841, "learning_rate": 3.531885217330314e-05, "loss": 0.33121374249458313, "step": 1163 }, { "epoch": 0.5069686411149826, "grad_norm": 2.0277304649353027, "learning_rate": 3.52809887571312e-05, "loss": 0.3832542896270752, "step": 1164 }, { "epoch": 0.507404181184669, "grad_norm": 2.225128173828125, "learning_rate": 3.524311665770016e-05, "loss": 0.3043123483657837, "step": 1165 }, { "epoch": 0.5078397212543554, "grad_norm": 1.8099216222763062, "learning_rate": 3.520523593728117e-05, "loss": 0.13923023641109467, "step": 1166 }, { "epoch": 0.5082752613240418, "grad_norm": 1.89533269405365, "learning_rate": 3.516734665815957e-05, "loss": 0.19309771060943604, "step": 1167 }, { "epoch": 0.5087108013937283, "grad_norm": 1.566048264503479, "learning_rate": 3.5129448882634746e-05, "loss": 0.22543549537658691, "step": 1168 }, { "epoch": 0.5091463414634146, "grad_norm": 1.5776112079620361, "learning_rate": 3.5091542673020067e-05, "loss": 0.15838418900966644, "step": 1169 }, { "epoch": 0.509581881533101, "grad_norm": 1.7228840589523315, "learning_rate": 3.505362809164278e-05, "loss": 0.15526948869228363, "step": 1170 }, { "epoch": 0.5100174216027874, "grad_norm": 1.9034383296966553, "learning_rate": 3.501570520084388e-05, "loss": 0.15756778419017792, "step": 1171 }, { "epoch": 0.5104529616724739, "grad_norm": 1.5244131088256836, "learning_rate": 3.497777406297804e-05, "loss": 0.14303278923034668, "step": 1172 }, { "epoch": 0.5108885017421603, "grad_norm": 1.6165560483932495, "learning_rate": 3.493983474041347e-05, "loss": 0.15983034670352936, "step": 1173 }, { "epoch": 0.5113240418118467, "grad_norm": 2.376225709915161, "learning_rate": 3.490188729553187e-05, "loss": 0.37235596776008606, "step": 1174 }, { "epoch": 0.5117595818815331, "grad_norm": 1.5993398427963257, "learning_rate": 3.486393179072827e-05, "loss": 0.1570022702217102, "step": 1175 }, { "epoch": 0.5121951219512195, "grad_norm": 1.8028088808059692, "learning_rate": 3.482596828841095e-05, "loss": 0.32625892758369446, "step": 1176 }, { "epoch": 0.5126306620209059, "grad_norm": 1.747727632522583, "learning_rate": 3.478799685100138e-05, "loss": 0.14791378378868103, "step": 1177 }, { "epoch": 0.5130662020905923, "grad_norm": 3.087388753890991, "learning_rate": 3.475001754093402e-05, "loss": 0.34930557012557983, "step": 1178 }, { "epoch": 0.5135017421602788, "grad_norm": 2.1234850883483887, "learning_rate": 3.471203042065632e-05, "loss": 0.431566059589386, "step": 1179 }, { "epoch": 0.5139372822299652, "grad_norm": 2.2144737243652344, "learning_rate": 3.467403555262855e-05, "loss": 0.16848622262477875, "step": 1180 }, { "epoch": 0.5143728222996515, "grad_norm": 1.3118842840194702, "learning_rate": 3.463603299932371e-05, "loss": 0.13345350325107574, "step": 1181 }, { "epoch": 0.514808362369338, "grad_norm": 2.0039496421813965, "learning_rate": 3.4598022823227476e-05, "loss": 0.22919665277004242, "step": 1182 }, { "epoch": 0.5152439024390244, "grad_norm": 2.303839921951294, "learning_rate": 3.456000508683802e-05, "loss": 0.4300968050956726, "step": 1183 }, { "epoch": 0.5156794425087108, "grad_norm": 1.6594644784927368, "learning_rate": 3.452197985266594e-05, "loss": 0.23674441874027252, "step": 1184 }, { "epoch": 0.5161149825783972, "grad_norm": 1.461106538772583, "learning_rate": 3.448394718323421e-05, "loss": 0.07900139689445496, "step": 1185 }, { "epoch": 0.5165505226480837, "grad_norm": 1.8544007539749146, "learning_rate": 3.444590714107798e-05, "loss": 0.21660542488098145, "step": 1186 }, { "epoch": 0.51698606271777, "grad_norm": 1.869638204574585, "learning_rate": 3.4407859788744545e-05, "loss": 0.2114979773759842, "step": 1187 }, { "epoch": 0.5174216027874564, "grad_norm": 1.802417278289795, "learning_rate": 3.4369805188793206e-05, "loss": 0.2311743199825287, "step": 1188 }, { "epoch": 0.5178571428571429, "grad_norm": 2.32055926322937, "learning_rate": 3.433174340379521e-05, "loss": 0.3279076814651489, "step": 1189 }, { "epoch": 0.5182926829268293, "grad_norm": 1.6646573543548584, "learning_rate": 3.429367449633359e-05, "loss": 0.1886872500181198, "step": 1190 }, { "epoch": 0.5187282229965157, "grad_norm": 1.6114059686660767, "learning_rate": 3.425559852900309e-05, "loss": 0.2587176561355591, "step": 1191 }, { "epoch": 0.519163763066202, "grad_norm": 1.9697712659835815, "learning_rate": 3.421751556441009e-05, "loss": 0.09466700255870819, "step": 1192 }, { "epoch": 0.5195993031358885, "grad_norm": 2.4811038970947266, "learning_rate": 3.417942566517244e-05, "loss": 0.33618924021720886, "step": 1193 }, { "epoch": 0.5200348432055749, "grad_norm": 1.917385458946228, "learning_rate": 3.4141328893919414e-05, "loss": 0.1491500437259674, "step": 1194 }, { "epoch": 0.5204703832752613, "grad_norm": 1.5917587280273438, "learning_rate": 3.410322531329159e-05, "loss": 0.13428331911563873, "step": 1195 }, { "epoch": 0.5209059233449478, "grad_norm": 1.4825680255889893, "learning_rate": 3.406511498594073e-05, "loss": 0.1241784542798996, "step": 1196 }, { "epoch": 0.5213414634146342, "grad_norm": 3.384349822998047, "learning_rate": 3.4026997974529664e-05, "loss": 0.2842749357223511, "step": 1197 }, { "epoch": 0.5217770034843205, "grad_norm": 1.7655137777328491, "learning_rate": 3.3988874341732276e-05, "loss": 0.2610293924808502, "step": 1198 }, { "epoch": 0.5222125435540069, "grad_norm": 2.328199625015259, "learning_rate": 3.395074415023328e-05, "loss": 0.30532899498939514, "step": 1199 }, { "epoch": 0.5226480836236934, "grad_norm": 1.7174396514892578, "learning_rate": 3.39126074627282e-05, "loss": 0.17889715731143951, "step": 1200 }, { "epoch": 0.5230836236933798, "grad_norm": 2.180039167404175, "learning_rate": 3.3874464341923244e-05, "loss": 0.1788996458053589, "step": 1201 }, { "epoch": 0.5235191637630662, "grad_norm": 2.207991361618042, "learning_rate": 3.383631485053518e-05, "loss": 0.3017471730709076, "step": 1202 }, { "epoch": 0.5239547038327527, "grad_norm": 2.007570505142212, "learning_rate": 3.379815905129127e-05, "loss": 0.2740532159805298, "step": 1203 }, { "epoch": 0.524390243902439, "grad_norm": 2.6844675540924072, "learning_rate": 3.375999700692913e-05, "loss": 0.2996765971183777, "step": 1204 }, { "epoch": 0.5248257839721254, "grad_norm": 1.8296564817428589, "learning_rate": 3.372182878019666e-05, "loss": 0.21368324756622314, "step": 1205 }, { "epoch": 0.5252613240418118, "grad_norm": 1.608399510383606, "learning_rate": 3.3683654433851914e-05, "loss": 0.14496062695980072, "step": 1206 }, { "epoch": 0.5256968641114983, "grad_norm": 1.9042320251464844, "learning_rate": 3.364547403066302e-05, "loss": 0.21680139005184174, "step": 1207 }, { "epoch": 0.5261324041811847, "grad_norm": 1.4270693063735962, "learning_rate": 3.3607287633408037e-05, "loss": 0.15794909000396729, "step": 1208 }, { "epoch": 0.5265679442508711, "grad_norm": 1.8294495344161987, "learning_rate": 3.356909530487492e-05, "loss": 0.22055114805698395, "step": 1209 }, { "epoch": 0.5270034843205574, "grad_norm": 2.3380329608917236, "learning_rate": 3.3530897107861365e-05, "loss": 0.2998453974723816, "step": 1210 }, { "epoch": 0.5274390243902439, "grad_norm": 2.5526046752929688, "learning_rate": 3.3492693105174685e-05, "loss": 0.39311784505844116, "step": 1211 }, { "epoch": 0.5278745644599303, "grad_norm": 1.4096437692642212, "learning_rate": 3.345448335963179e-05, "loss": 0.1659044325351715, "step": 1212 }, { "epoch": 0.5283101045296167, "grad_norm": 1.2947112321853638, "learning_rate": 3.341626793405897e-05, "loss": 0.10156561434268951, "step": 1213 }, { "epoch": 0.5287456445993032, "grad_norm": 1.7225115299224854, "learning_rate": 3.3378046891291934e-05, "loss": 0.1789904683828354, "step": 1214 }, { "epoch": 0.5291811846689896, "grad_norm": 4.889913558959961, "learning_rate": 3.333982029417554e-05, "loss": 0.4171358048915863, "step": 1215 }, { "epoch": 0.5296167247386759, "grad_norm": 1.4743788242340088, "learning_rate": 3.330158820556385e-05, "loss": 0.27201035618782043, "step": 1216 }, { "epoch": 0.5300522648083623, "grad_norm": 1.5995657444000244, "learning_rate": 3.326335068831993e-05, "loss": 0.19408534467220306, "step": 1217 }, { "epoch": 0.5304878048780488, "grad_norm": 2.2095787525177, "learning_rate": 3.3225107805315755e-05, "loss": 0.32811084389686584, "step": 1218 }, { "epoch": 0.5309233449477352, "grad_norm": 2.0387096405029297, "learning_rate": 3.318685961943213e-05, "loss": 0.1461152732372284, "step": 1219 }, { "epoch": 0.5313588850174216, "grad_norm": 2.2667713165283203, "learning_rate": 3.3148606193558615e-05, "loss": 0.288274884223938, "step": 1220 }, { "epoch": 0.5317944250871081, "grad_norm": 2.238816499710083, "learning_rate": 3.3110347590593325e-05, "loss": 0.4841238260269165, "step": 1221 }, { "epoch": 0.5322299651567944, "grad_norm": 1.9166923761367798, "learning_rate": 3.307208387344294e-05, "loss": 0.2227621227502823, "step": 1222 }, { "epoch": 0.5326655052264808, "grad_norm": 1.569441318511963, "learning_rate": 3.3033815105022534e-05, "loss": 0.21309727430343628, "step": 1223 }, { "epoch": 0.5331010452961672, "grad_norm": 1.1066712141036987, "learning_rate": 3.299554134825546e-05, "loss": 0.08630914241075516, "step": 1224 }, { "epoch": 0.5335365853658537, "grad_norm": 2.3179972171783447, "learning_rate": 3.295726266607331e-05, "loss": 0.3639899790287018, "step": 1225 }, { "epoch": 0.5339721254355401, "grad_norm": 1.635815143585205, "learning_rate": 3.291897912141575e-05, "loss": 0.21737079322338104, "step": 1226 }, { "epoch": 0.5344076655052264, "grad_norm": 2.0886831283569336, "learning_rate": 3.288069077723045e-05, "loss": 0.18231910467147827, "step": 1227 }, { "epoch": 0.5348432055749129, "grad_norm": 3.154646635055542, "learning_rate": 3.284239769647299e-05, "loss": 0.37354663014411926, "step": 1228 }, { "epoch": 0.5352787456445993, "grad_norm": 2.3170626163482666, "learning_rate": 3.2804099942106694e-05, "loss": 0.305888295173645, "step": 1229 }, { "epoch": 0.5357142857142857, "grad_norm": 1.8952364921569824, "learning_rate": 3.2765797577102604e-05, "loss": 0.3440328538417816, "step": 1230 }, { "epoch": 0.5361498257839721, "grad_norm": 2.112996816635132, "learning_rate": 3.272749066443935e-05, "loss": 0.2392309457063675, "step": 1231 }, { "epoch": 0.5365853658536586, "grad_norm": 2.070981979370117, "learning_rate": 3.2689179267103005e-05, "loss": 0.36750540137290955, "step": 1232 }, { "epoch": 0.537020905923345, "grad_norm": 1.621617317199707, "learning_rate": 3.265086344808705e-05, "loss": 0.24706138670444489, "step": 1233 }, { "epoch": 0.5374564459930313, "grad_norm": 1.8779127597808838, "learning_rate": 3.261254327039221e-05, "loss": 0.23273688554763794, "step": 1234 }, { "epoch": 0.5378919860627178, "grad_norm": 1.821108102798462, "learning_rate": 3.25742187970264e-05, "loss": 0.2509998679161072, "step": 1235 }, { "epoch": 0.5383275261324042, "grad_norm": 2.29180908203125, "learning_rate": 3.2535890091004584e-05, "loss": 0.17620037496089935, "step": 1236 }, { "epoch": 0.5387630662020906, "grad_norm": 1.5747777223587036, "learning_rate": 3.249755721534868e-05, "loss": 0.17062820494174957, "step": 1237 }, { "epoch": 0.539198606271777, "grad_norm": 1.5021144151687622, "learning_rate": 3.245922023308748e-05, "loss": 0.10165175795555115, "step": 1238 }, { "epoch": 0.5396341463414634, "grad_norm": 1.633527398109436, "learning_rate": 3.242087920725652e-05, "loss": 0.20993205904960632, "step": 1239 }, { "epoch": 0.5400696864111498, "grad_norm": 1.874335765838623, "learning_rate": 3.2382534200897984e-05, "loss": 0.31201937794685364, "step": 1240 }, { "epoch": 0.5405052264808362, "grad_norm": 1.641734004020691, "learning_rate": 3.2344185277060574e-05, "loss": 0.17482449114322662, "step": 1241 }, { "epoch": 0.5409407665505227, "grad_norm": 1.4150607585906982, "learning_rate": 3.23058324987995e-05, "loss": 0.13866113126277924, "step": 1242 }, { "epoch": 0.5413763066202091, "grad_norm": 1.8492851257324219, "learning_rate": 3.2267475929176245e-05, "loss": 0.21408431231975555, "step": 1243 }, { "epoch": 0.5418118466898955, "grad_norm": 2.711221694946289, "learning_rate": 3.2229115631258555e-05, "loss": 0.31324562430381775, "step": 1244 }, { "epoch": 0.5422473867595818, "grad_norm": 2.0511374473571777, "learning_rate": 3.21907516681203e-05, "loss": 0.28373023867607117, "step": 1245 }, { "epoch": 0.5426829268292683, "grad_norm": 2.208960771560669, "learning_rate": 3.215238410284138e-05, "loss": 0.3316265046596527, "step": 1246 }, { "epoch": 0.5431184668989547, "grad_norm": 4.207181930541992, "learning_rate": 3.2114012998507616e-05, "loss": 0.27299079298973083, "step": 1247 }, { "epoch": 0.5435540069686411, "grad_norm": 1.8766871690750122, "learning_rate": 3.207563841821065e-05, "loss": 0.20722706615924835, "step": 1248 }, { "epoch": 0.5439895470383276, "grad_norm": 1.4189461469650269, "learning_rate": 3.203726042504784e-05, "loss": 0.14890773594379425, "step": 1249 }, { "epoch": 0.544425087108014, "grad_norm": 2.4780664443969727, "learning_rate": 3.199887908212213e-05, "loss": 0.36084049940109253, "step": 1250 }, { "epoch": 0.5448606271777003, "grad_norm": 2.4032413959503174, "learning_rate": 3.1960494452542026e-05, "loss": 0.24586418271064758, "step": 1251 }, { "epoch": 0.5452961672473867, "grad_norm": 1.9923304319381714, "learning_rate": 3.192210659942139e-05, "loss": 0.22625204920768738, "step": 1252 }, { "epoch": 0.5457317073170732, "grad_norm": 1.7670695781707764, "learning_rate": 3.1883715585879403e-05, "loss": 0.19027359783649445, "step": 1253 }, { "epoch": 0.5461672473867596, "grad_norm": 2.9382357597351074, "learning_rate": 3.1845321475040447e-05, "loss": 0.30525535345077515, "step": 1254 }, { "epoch": 0.546602787456446, "grad_norm": 1.6029062271118164, "learning_rate": 3.180692433003398e-05, "loss": 0.2019837498664856, "step": 1255 }, { "epoch": 0.5470383275261324, "grad_norm": 1.9566453695297241, "learning_rate": 3.1768524213994456e-05, "loss": 0.21185468137264252, "step": 1256 }, { "epoch": 0.5474738675958188, "grad_norm": 4.819205284118652, "learning_rate": 3.173012119006124e-05, "loss": 0.48035016655921936, "step": 1257 }, { "epoch": 0.5479094076655052, "grad_norm": 2.2356154918670654, "learning_rate": 3.169171532137843e-05, "loss": 0.2236589938402176, "step": 1258 }, { "epoch": 0.5483449477351916, "grad_norm": 1.9171613454818726, "learning_rate": 3.1653306671094847e-05, "loss": 0.2532399594783783, "step": 1259 }, { "epoch": 0.5487804878048781, "grad_norm": 1.9234936237335205, "learning_rate": 3.161489530236385e-05, "loss": 0.25687175989151, "step": 1260 }, { "epoch": 0.5492160278745645, "grad_norm": 1.8263360261917114, "learning_rate": 3.157648127834329e-05, "loss": 0.2603629231452942, "step": 1261 }, { "epoch": 0.5496515679442509, "grad_norm": 1.8392120599746704, "learning_rate": 3.153806466219537e-05, "loss": 0.18183012306690216, "step": 1262 }, { "epoch": 0.5500871080139372, "grad_norm": 1.6939584016799927, "learning_rate": 3.14996455170866e-05, "loss": 0.2842605710029602, "step": 1263 }, { "epoch": 0.5505226480836237, "grad_norm": 2.3518311977386475, "learning_rate": 3.146122390618756e-05, "loss": 0.27841368317604065, "step": 1264 }, { "epoch": 0.5509581881533101, "grad_norm": 1.8106794357299805, "learning_rate": 3.142279989267296e-05, "loss": 0.21881335973739624, "step": 1265 }, { "epoch": 0.5513937282229965, "grad_norm": 2.3070802688598633, "learning_rate": 3.138437353972143e-05, "loss": 0.1949990689754486, "step": 1266 }, { "epoch": 0.551829268292683, "grad_norm": 1.702703833580017, "learning_rate": 3.134594491051545e-05, "loss": 0.2028479278087616, "step": 1267 }, { "epoch": 0.5522648083623694, "grad_norm": 1.9420315027236938, "learning_rate": 3.130751406824125e-05, "loss": 0.37364858388900757, "step": 1268 }, { "epoch": 0.5527003484320557, "grad_norm": 1.7197920083999634, "learning_rate": 3.12690810760887e-05, "loss": 0.14771635830402374, "step": 1269 }, { "epoch": 0.5531358885017421, "grad_norm": 1.8778204917907715, "learning_rate": 3.12306459972512e-05, "loss": 0.2707819640636444, "step": 1270 }, { "epoch": 0.5535714285714286, "grad_norm": 1.841740608215332, "learning_rate": 3.1192208894925563e-05, "loss": 0.2295936495065689, "step": 1271 }, { "epoch": 0.554006968641115, "grad_norm": 2.285933256149292, "learning_rate": 3.115376983231195e-05, "loss": 0.5062440037727356, "step": 1272 }, { "epoch": 0.5544425087108014, "grad_norm": 1.6756864786148071, "learning_rate": 3.1115328872613756e-05, "loss": 0.2305927574634552, "step": 1273 }, { "epoch": 0.5548780487804879, "grad_norm": 2.0271458625793457, "learning_rate": 3.107688607903747e-05, "loss": 0.4064762592315674, "step": 1274 }, { "epoch": 0.5553135888501742, "grad_norm": 1.804175853729248, "learning_rate": 3.1038441514792605e-05, "loss": 0.17976224422454834, "step": 1275 }, { "epoch": 0.5557491289198606, "grad_norm": 1.3519315719604492, "learning_rate": 3.099999524309159e-05, "loss": 0.1335075944662094, "step": 1276 }, { "epoch": 0.556184668989547, "grad_norm": 2.3050198554992676, "learning_rate": 3.0961547327149664e-05, "loss": 0.37646085023880005, "step": 1277 }, { "epoch": 0.5566202090592335, "grad_norm": 1.556321620941162, "learning_rate": 3.0923097830184744e-05, "loss": 0.16961856186389923, "step": 1278 }, { "epoch": 0.5570557491289199, "grad_norm": 1.4097685813903809, "learning_rate": 3.08846468154174e-05, "loss": 0.15099835395812988, "step": 1279 }, { "epoch": 0.5574912891986062, "grad_norm": 1.4505740404129028, "learning_rate": 3.084619434607064e-05, "loss": 0.15777641534805298, "step": 1280 }, { "epoch": 0.5579268292682927, "grad_norm": 2.450674295425415, "learning_rate": 3.0807740485369885e-05, "loss": 0.21230410039424896, "step": 1281 }, { "epoch": 0.5583623693379791, "grad_norm": 1.1216990947723389, "learning_rate": 3.076928529654286e-05, "loss": 0.14416974782943726, "step": 1282 }, { "epoch": 0.5587979094076655, "grad_norm": 1.64701509475708, "learning_rate": 3.0730828842819464e-05, "loss": 0.19795680046081543, "step": 1283 }, { "epoch": 0.5592334494773519, "grad_norm": 0.9094190001487732, "learning_rate": 3.0692371187431666e-05, "loss": 0.058812882751226425, "step": 1284 }, { "epoch": 0.5596689895470384, "grad_norm": 2.024871826171875, "learning_rate": 3.065391239361342e-05, "loss": 0.33459240198135376, "step": 1285 }, { "epoch": 0.5601045296167247, "grad_norm": 3.09110689163208, "learning_rate": 3.061545252460054e-05, "loss": 0.35857725143432617, "step": 1286 }, { "epoch": 0.5605400696864111, "grad_norm": 2.1968157291412354, "learning_rate": 3.0576991643630613e-05, "loss": 0.23262721300125122, "step": 1287 }, { "epoch": 0.5609756097560976, "grad_norm": 1.2886687517166138, "learning_rate": 3.053852981394292e-05, "loss": 0.11715119332075119, "step": 1288 }, { "epoch": 0.561411149825784, "grad_norm": 2.3213162422180176, "learning_rate": 3.0500067098778254e-05, "loss": 0.3626524806022644, "step": 1289 }, { "epoch": 0.5618466898954704, "grad_norm": 1.813779592514038, "learning_rate": 3.04616035613789e-05, "loss": 0.2000131905078888, "step": 1290 }, { "epoch": 0.5622822299651568, "grad_norm": 1.3687902688980103, "learning_rate": 3.042313926498846e-05, "loss": 0.18496592342853546, "step": 1291 }, { "epoch": 0.5627177700348432, "grad_norm": 1.859156847000122, "learning_rate": 3.038467427285182e-05, "loss": 0.2613186836242676, "step": 1292 }, { "epoch": 0.5631533101045296, "grad_norm": 1.7429312467575073, "learning_rate": 3.0346208648215e-05, "loss": 0.23041483759880066, "step": 1293 }, { "epoch": 0.563588850174216, "grad_norm": 1.0485212802886963, "learning_rate": 3.030774245432504e-05, "loss": 0.10163982212543488, "step": 1294 }, { "epoch": 0.5640243902439024, "grad_norm": 7.012165069580078, "learning_rate": 3.0269275754429935e-05, "loss": 0.14100025594234467, "step": 1295 }, { "epoch": 0.5644599303135889, "grad_norm": 1.5873467922210693, "learning_rate": 3.023080861177852e-05, "loss": 0.14654625952243805, "step": 1296 }, { "epoch": 0.5648954703832753, "grad_norm": 1.2404553890228271, "learning_rate": 3.0192341089620336e-05, "loss": 0.11249801516532898, "step": 1297 }, { "epoch": 0.5653310104529616, "grad_norm": 2.113356351852417, "learning_rate": 3.015387325120555e-05, "loss": 0.27745190262794495, "step": 1298 }, { "epoch": 0.5657665505226481, "grad_norm": 2.2082254886627197, "learning_rate": 3.0115405159784878e-05, "loss": 0.1680198311805725, "step": 1299 }, { "epoch": 0.5662020905923345, "grad_norm": 2.425495147705078, "learning_rate": 3.0076936878609406e-05, "loss": 0.22404608130455017, "step": 1300 }, { "epoch": 0.5666376306620209, "grad_norm": 1.8488414287567139, "learning_rate": 3.0038468470930572e-05, "loss": 0.30183571577072144, "step": 1301 }, { "epoch": 0.5670731707317073, "grad_norm": 2.0390195846557617, "learning_rate": 3e-05, "loss": 0.26834002137184143, "step": 1302 }, { "epoch": 0.5675087108013938, "grad_norm": 1.1455984115600586, "learning_rate": 2.996153152906943e-05, "loss": 0.14714863896369934, "step": 1303 }, { "epoch": 0.5679442508710801, "grad_norm": 1.4030210971832275, "learning_rate": 2.99230631213906e-05, "loss": 0.21118777990341187, "step": 1304 }, { "epoch": 0.5683797909407665, "grad_norm": 1.6535847187042236, "learning_rate": 2.9884594840215127e-05, "loss": 0.13989926874637604, "step": 1305 }, { "epoch": 0.568815331010453, "grad_norm": 2.3527426719665527, "learning_rate": 2.9846126748794452e-05, "loss": 0.37161001563072205, "step": 1306 }, { "epoch": 0.5692508710801394, "grad_norm": 1.2818504571914673, "learning_rate": 2.9807658910379666e-05, "loss": 0.13303937017917633, "step": 1307 }, { "epoch": 0.5696864111498258, "grad_norm": 1.7819384336471558, "learning_rate": 2.9769191388221476e-05, "loss": 0.24990375339984894, "step": 1308 }, { "epoch": 0.5701219512195121, "grad_norm": 1.0550129413604736, "learning_rate": 2.9730724245570063e-05, "loss": 0.1301070749759674, "step": 1309 }, { "epoch": 0.5705574912891986, "grad_norm": 2.0256078243255615, "learning_rate": 2.969225754567496e-05, "loss": 0.3316114842891693, "step": 1310 }, { "epoch": 0.570993031358885, "grad_norm": 1.8508574962615967, "learning_rate": 2.9653791351785e-05, "loss": 0.1672663539648056, "step": 1311 }, { "epoch": 0.5714285714285714, "grad_norm": 2.407881498336792, "learning_rate": 2.961532572714818e-05, "loss": 0.3688102066516876, "step": 1312 }, { "epoch": 0.5718641114982579, "grad_norm": 1.7426962852478027, "learning_rate": 2.957686073501154e-05, "loss": 0.213697612285614, "step": 1313 }, { "epoch": 0.5722996515679443, "grad_norm": 2.3700451850891113, "learning_rate": 2.9538396438621115e-05, "loss": 0.2450462281703949, "step": 1314 }, { "epoch": 0.5727351916376306, "grad_norm": 2.261808395385742, "learning_rate": 2.9499932901221758e-05, "loss": 0.2895894944667816, "step": 1315 }, { "epoch": 0.573170731707317, "grad_norm": 1.5829752683639526, "learning_rate": 2.946147018605709e-05, "loss": 0.2187323421239853, "step": 1316 }, { "epoch": 0.5736062717770035, "grad_norm": 2.046006202697754, "learning_rate": 2.9423008356369388e-05, "loss": 0.2683967649936676, "step": 1317 }, { "epoch": 0.5740418118466899, "grad_norm": 2.077106237411499, "learning_rate": 2.9384547475399473e-05, "loss": 0.2140924483537674, "step": 1318 }, { "epoch": 0.5744773519163763, "grad_norm": 1.467585802078247, "learning_rate": 2.9346087606386592e-05, "loss": 0.15292803943157196, "step": 1319 }, { "epoch": 0.5749128919860628, "grad_norm": 1.266112208366394, "learning_rate": 2.9307628812568342e-05, "loss": 0.13219943642616272, "step": 1320 }, { "epoch": 0.5753484320557491, "grad_norm": 1.6740564107894897, "learning_rate": 2.926917115718054e-05, "loss": 0.208161860704422, "step": 1321 }, { "epoch": 0.5757839721254355, "grad_norm": 1.595106840133667, "learning_rate": 2.923071470345714e-05, "loss": 0.16393855214118958, "step": 1322 }, { "epoch": 0.5762195121951219, "grad_norm": 2.0885729789733887, "learning_rate": 2.9192259514630123e-05, "loss": 0.35919564962387085, "step": 1323 }, { "epoch": 0.5766550522648084, "grad_norm": 1.5314321517944336, "learning_rate": 2.915380565392937e-05, "loss": 0.17880970239639282, "step": 1324 }, { "epoch": 0.5770905923344948, "grad_norm": 2.275857925415039, "learning_rate": 2.9115353184582605e-05, "loss": 0.37783944606781006, "step": 1325 }, { "epoch": 0.5775261324041812, "grad_norm": 1.8927205801010132, "learning_rate": 2.9076902169815257e-05, "loss": 0.23611073195934296, "step": 1326 }, { "epoch": 0.5779616724738676, "grad_norm": 1.5297832489013672, "learning_rate": 2.9038452672850344e-05, "loss": 0.17640087008476257, "step": 1327 }, { "epoch": 0.578397212543554, "grad_norm": 1.7052741050720215, "learning_rate": 2.900000475690842e-05, "loss": 0.1636761575937271, "step": 1328 }, { "epoch": 0.5788327526132404, "grad_norm": 1.6927305459976196, "learning_rate": 2.89615584852074e-05, "loss": 0.2173040211200714, "step": 1329 }, { "epoch": 0.5792682926829268, "grad_norm": 2.084845781326294, "learning_rate": 2.892311392096253e-05, "loss": 0.2786039710044861, "step": 1330 }, { "epoch": 0.5797038327526133, "grad_norm": 1.7768523693084717, "learning_rate": 2.888467112738625e-05, "loss": 0.13360758125782013, "step": 1331 }, { "epoch": 0.5801393728222997, "grad_norm": 1.589676856994629, "learning_rate": 2.8846230167688048e-05, "loss": 0.16625314950942993, "step": 1332 }, { "epoch": 0.580574912891986, "grad_norm": 2.070446252822876, "learning_rate": 2.8807791105074445e-05, "loss": 0.3192163109779358, "step": 1333 }, { "epoch": 0.5810104529616724, "grad_norm": 1.8861228227615356, "learning_rate": 2.8769354002748805e-05, "loss": 0.3069511353969574, "step": 1334 }, { "epoch": 0.5814459930313589, "grad_norm": 2.25631046295166, "learning_rate": 2.8730918923911293e-05, "loss": 0.3152622580528259, "step": 1335 }, { "epoch": 0.5818815331010453, "grad_norm": 1.834847092628479, "learning_rate": 2.8692485931758745e-05, "loss": 0.25460171699523926, "step": 1336 }, { "epoch": 0.5823170731707317, "grad_norm": 2.2597529888153076, "learning_rate": 2.8654055089484563e-05, "loss": 0.24117185175418854, "step": 1337 }, { "epoch": 0.5827526132404182, "grad_norm": 1.744492769241333, "learning_rate": 2.8615626460278587e-05, "loss": 0.2260976880788803, "step": 1338 }, { "epoch": 0.5831881533101045, "grad_norm": 1.4152963161468506, "learning_rate": 2.857720010732705e-05, "loss": 0.12728485465049744, "step": 1339 }, { "epoch": 0.5836236933797909, "grad_norm": 1.6194369792938232, "learning_rate": 2.8538776093812453e-05, "loss": 0.1628914326429367, "step": 1340 }, { "epoch": 0.5840592334494773, "grad_norm": 1.4098714590072632, "learning_rate": 2.8500354482913416e-05, "loss": 0.1331072449684143, "step": 1341 }, { "epoch": 0.5844947735191638, "grad_norm": 1.860482931137085, "learning_rate": 2.846193533780463e-05, "loss": 0.24004779756069183, "step": 1342 }, { "epoch": 0.5849303135888502, "grad_norm": 1.4867013692855835, "learning_rate": 2.8423518721656715e-05, "loss": 0.16906633973121643, "step": 1343 }, { "epoch": 0.5853658536585366, "grad_norm": 1.4931787252426147, "learning_rate": 2.8385104697636157e-05, "loss": 0.26338085532188416, "step": 1344 }, { "epoch": 0.585801393728223, "grad_norm": 1.8244421482086182, "learning_rate": 2.8346693328905165e-05, "loss": 0.18665918707847595, "step": 1345 }, { "epoch": 0.5862369337979094, "grad_norm": 1.7508691549301147, "learning_rate": 2.830828467862157e-05, "loss": 0.2500062882900238, "step": 1346 }, { "epoch": 0.5866724738675958, "grad_norm": 1.7115296125411987, "learning_rate": 2.826987880993877e-05, "loss": 0.2515639364719391, "step": 1347 }, { "epoch": 0.5871080139372822, "grad_norm": 1.9816491603851318, "learning_rate": 2.8231475786005545e-05, "loss": 0.2780587077140808, "step": 1348 }, { "epoch": 0.5875435540069687, "grad_norm": 2.2995188236236572, "learning_rate": 2.8193075669966027e-05, "loss": 0.30068239569664, "step": 1349 }, { "epoch": 0.587979094076655, "grad_norm": 1.5038076639175415, "learning_rate": 2.8154678524959562e-05, "loss": 0.21021251380443573, "step": 1350 }, { "epoch": 0.5884146341463414, "grad_norm": 1.6126465797424316, "learning_rate": 2.81162844141206e-05, "loss": 0.17707999050617218, "step": 1351 }, { "epoch": 0.5888501742160279, "grad_norm": 1.9491106271743774, "learning_rate": 2.8077893400578617e-05, "loss": 0.32348909974098206, "step": 1352 }, { "epoch": 0.5892857142857143, "grad_norm": 2.091373920440674, "learning_rate": 2.8039505547457975e-05, "loss": 0.2754712700843811, "step": 1353 }, { "epoch": 0.5897212543554007, "grad_norm": 3.753204822540283, "learning_rate": 2.8001120917877865e-05, "loss": 0.2297249734401703, "step": 1354 }, { "epoch": 0.5901567944250871, "grad_norm": 1.9606746435165405, "learning_rate": 2.796273957495217e-05, "loss": 0.19272969663143158, "step": 1355 }, { "epoch": 0.5905923344947736, "grad_norm": 1.5958508253097534, "learning_rate": 2.792436158178935e-05, "loss": 0.22788110375404358, "step": 1356 }, { "epoch": 0.5910278745644599, "grad_norm": 1.4589847326278687, "learning_rate": 2.788598700149238e-05, "loss": 0.1278601884841919, "step": 1357 }, { "epoch": 0.5914634146341463, "grad_norm": 1.551324486732483, "learning_rate": 2.784761589715862e-05, "loss": 0.16612817347049713, "step": 1358 }, { "epoch": 0.5918989547038328, "grad_norm": 2.1214427947998047, "learning_rate": 2.7809248331879712e-05, "loss": 0.3975890576839447, "step": 1359 }, { "epoch": 0.5923344947735192, "grad_norm": 1.8399595022201538, "learning_rate": 2.7770884368741453e-05, "loss": 0.21396517753601074, "step": 1360 }, { "epoch": 0.5927700348432056, "grad_norm": 2.1628801822662354, "learning_rate": 2.7732524070823767e-05, "loss": 0.18176965415477753, "step": 1361 }, { "epoch": 0.5932055749128919, "grad_norm": 1.2781883478164673, "learning_rate": 2.7694167501200508e-05, "loss": 0.14342190325260162, "step": 1362 }, { "epoch": 0.5936411149825784, "grad_norm": 1.6835523843765259, "learning_rate": 2.7655814722939424e-05, "loss": 0.21892698109149933, "step": 1363 }, { "epoch": 0.5940766550522648, "grad_norm": 2.2439956665039062, "learning_rate": 2.761746579910203e-05, "loss": 0.2719407379627228, "step": 1364 }, { "epoch": 0.5945121951219512, "grad_norm": 1.4128025770187378, "learning_rate": 2.7579120792743485e-05, "loss": 0.08538347482681274, "step": 1365 }, { "epoch": 0.5949477351916377, "grad_norm": 1.1250094175338745, "learning_rate": 2.7540779766912526e-05, "loss": 0.09105332940816879, "step": 1366 }, { "epoch": 0.5953832752613241, "grad_norm": 2.4108567237854004, "learning_rate": 2.7502442784651323e-05, "loss": 0.35657840967178345, "step": 1367 }, { "epoch": 0.5958188153310104, "grad_norm": 1.3588026762008667, "learning_rate": 2.7464109908995418e-05, "loss": 0.16930775344371796, "step": 1368 }, { "epoch": 0.5962543554006968, "grad_norm": 1.4603877067565918, "learning_rate": 2.7425781202973603e-05, "loss": 0.1897612363100052, "step": 1369 }, { "epoch": 0.5966898954703833, "grad_norm": 2.2575597763061523, "learning_rate": 2.738745672960779e-05, "loss": 0.3761543929576874, "step": 1370 }, { "epoch": 0.5971254355400697, "grad_norm": 1.516898512840271, "learning_rate": 2.734913655191295e-05, "loss": 0.1858750432729721, "step": 1371 }, { "epoch": 0.5975609756097561, "grad_norm": 2.0671823024749756, "learning_rate": 2.7310820732897e-05, "loss": 0.3544721007347107, "step": 1372 }, { "epoch": 0.5979965156794426, "grad_norm": 3.0401933193206787, "learning_rate": 2.7272509335560652e-05, "loss": 0.2851201593875885, "step": 1373 }, { "epoch": 0.5984320557491289, "grad_norm": 1.5025359392166138, "learning_rate": 2.7234202422897397e-05, "loss": 0.18936404585838318, "step": 1374 }, { "epoch": 0.5988675958188153, "grad_norm": 2.1338400840759277, "learning_rate": 2.7195900057893308e-05, "loss": 0.31363314390182495, "step": 1375 }, { "epoch": 0.5993031358885017, "grad_norm": 2.581341028213501, "learning_rate": 2.7157602303527014e-05, "loss": 0.36393266916275024, "step": 1376 }, { "epoch": 0.5997386759581882, "grad_norm": 2.0012505054473877, "learning_rate": 2.7119309222769548e-05, "loss": 0.26431789994239807, "step": 1377 }, { "epoch": 0.6001742160278746, "grad_norm": 3.6520750522613525, "learning_rate": 2.7081020878584252e-05, "loss": 0.128719300031662, "step": 1378 }, { "epoch": 0.600609756097561, "grad_norm": 1.5242259502410889, "learning_rate": 2.7042737333926696e-05, "loss": 0.1392907351255417, "step": 1379 }, { "epoch": 0.6010452961672473, "grad_norm": 2.1261560916900635, "learning_rate": 2.700445865174454e-05, "loss": 0.3186664581298828, "step": 1380 }, { "epoch": 0.6014808362369338, "grad_norm": 2.6157634258270264, "learning_rate": 2.6966184894977467e-05, "loss": 0.4460267424583435, "step": 1381 }, { "epoch": 0.6019163763066202, "grad_norm": 1.4706969261169434, "learning_rate": 2.692791612655706e-05, "loss": 0.17917637526988983, "step": 1382 }, { "epoch": 0.6023519163763066, "grad_norm": 1.9775458574295044, "learning_rate": 2.6889652409406683e-05, "loss": 0.28681322932243347, "step": 1383 }, { "epoch": 0.6027874564459931, "grad_norm": 2.0796120166778564, "learning_rate": 2.6851393806441396e-05, "loss": 0.3335949182510376, "step": 1384 }, { "epoch": 0.6032229965156795, "grad_norm": 1.4693139791488647, "learning_rate": 2.6813140380567873e-05, "loss": 0.15765881538391113, "step": 1385 }, { "epoch": 0.6036585365853658, "grad_norm": 1.385542392730713, "learning_rate": 2.677489219468426e-05, "loss": 0.14334559440612793, "step": 1386 }, { "epoch": 0.6040940766550522, "grad_norm": 1.5054854154586792, "learning_rate": 2.6736649311680076e-05, "loss": 0.12850937247276306, "step": 1387 }, { "epoch": 0.6045296167247387, "grad_norm": 1.60765540599823, "learning_rate": 2.6698411794436154e-05, "loss": 0.17463791370391846, "step": 1388 }, { "epoch": 0.6049651567944251, "grad_norm": 1.658469557762146, "learning_rate": 2.6660179705824463e-05, "loss": 0.21663358807563782, "step": 1389 }, { "epoch": 0.6054006968641115, "grad_norm": 1.7762863636016846, "learning_rate": 2.6621953108708078e-05, "loss": 0.22876380383968353, "step": 1390 }, { "epoch": 0.605836236933798, "grad_norm": 1.9468557834625244, "learning_rate": 2.6583732065941032e-05, "loss": 0.2954308092594147, "step": 1391 }, { "epoch": 0.6062717770034843, "grad_norm": 1.2998851537704468, "learning_rate": 2.654551664036822e-05, "loss": 0.12982992827892303, "step": 1392 }, { "epoch": 0.6067073170731707, "grad_norm": 1.5497297048568726, "learning_rate": 2.6507306894825317e-05, "loss": 0.19894252717494965, "step": 1393 }, { "epoch": 0.6071428571428571, "grad_norm": 1.7153383493423462, "learning_rate": 2.6469102892138643e-05, "loss": 0.24864396452903748, "step": 1394 }, { "epoch": 0.6075783972125436, "grad_norm": 2.5014488697052, "learning_rate": 2.6430904695125075e-05, "loss": 0.4285851716995239, "step": 1395 }, { "epoch": 0.60801393728223, "grad_norm": 2.284639835357666, "learning_rate": 2.639271236659197e-05, "loss": 0.3811066150665283, "step": 1396 }, { "epoch": 0.6084494773519163, "grad_norm": 1.377539873123169, "learning_rate": 2.635452596933699e-05, "loss": 0.12293872237205505, "step": 1397 }, { "epoch": 0.6088850174216028, "grad_norm": 1.8557617664337158, "learning_rate": 2.6316345566148098e-05, "loss": 0.2641359865665436, "step": 1398 }, { "epoch": 0.6093205574912892, "grad_norm": 2.0237460136413574, "learning_rate": 2.6278171219803345e-05, "loss": 0.23013053834438324, "step": 1399 }, { "epoch": 0.6097560975609756, "grad_norm": 1.3620203733444214, "learning_rate": 2.624000299307087e-05, "loss": 0.1309473067522049, "step": 1400 }, { "epoch": 0.610191637630662, "grad_norm": 1.7026824951171875, "learning_rate": 2.6201840948708736e-05, "loss": 0.17942121624946594, "step": 1401 }, { "epoch": 0.6106271777003485, "grad_norm": 2.0340354442596436, "learning_rate": 2.6163685149464815e-05, "loss": 0.26147156953811646, "step": 1402 }, { "epoch": 0.6110627177700348, "grad_norm": 2.0781233310699463, "learning_rate": 2.612553565807675e-05, "loss": 0.2737745940685272, "step": 1403 }, { "epoch": 0.6114982578397212, "grad_norm": 1.4551810026168823, "learning_rate": 2.6087392537271797e-05, "loss": 0.11400774121284485, "step": 1404 }, { "epoch": 0.6119337979094077, "grad_norm": 1.3631961345672607, "learning_rate": 2.6049255849766727e-05, "loss": 0.10554643720388412, "step": 1405 }, { "epoch": 0.6123693379790941, "grad_norm": 1.4406837224960327, "learning_rate": 2.6011125658267736e-05, "loss": 0.10089446604251862, "step": 1406 }, { "epoch": 0.6128048780487805, "grad_norm": 1.8493452072143555, "learning_rate": 2.5973002025470347e-05, "loss": 0.2563517391681671, "step": 1407 }, { "epoch": 0.6132404181184669, "grad_norm": 1.1026527881622314, "learning_rate": 2.5934885014059287e-05, "loss": 0.0937824472784996, "step": 1408 }, { "epoch": 0.6136759581881533, "grad_norm": 1.3296196460723877, "learning_rate": 2.5896774686708412e-05, "loss": 0.10880471020936966, "step": 1409 }, { "epoch": 0.6141114982578397, "grad_norm": 1.5937347412109375, "learning_rate": 2.5858671106080588e-05, "loss": 0.2239312380552292, "step": 1410 }, { "epoch": 0.6145470383275261, "grad_norm": 2.168644428253174, "learning_rate": 2.5820574334827564e-05, "loss": 0.39461448788642883, "step": 1411 }, { "epoch": 0.6149825783972126, "grad_norm": 1.7165617942810059, "learning_rate": 2.578248443558992e-05, "loss": 0.20071062445640564, "step": 1412 }, { "epoch": 0.615418118466899, "grad_norm": 1.0566691160202026, "learning_rate": 2.5744401470996912e-05, "loss": 0.06137409806251526, "step": 1413 }, { "epoch": 0.6158536585365854, "grad_norm": 2.2507987022399902, "learning_rate": 2.5706325503666417e-05, "loss": 0.27774739265441895, "step": 1414 }, { "epoch": 0.6162891986062717, "grad_norm": 1.6252764463424683, "learning_rate": 2.56682565962048e-05, "loss": 0.22203701734542847, "step": 1415 }, { "epoch": 0.6167247386759582, "grad_norm": 1.9125720262527466, "learning_rate": 2.5630194811206795e-05, "loss": 0.35589826107025146, "step": 1416 }, { "epoch": 0.6171602787456446, "grad_norm": 1.7730011940002441, "learning_rate": 2.5592140211255463e-05, "loss": 0.2606363296508789, "step": 1417 }, { "epoch": 0.617595818815331, "grad_norm": 2.4187750816345215, "learning_rate": 2.555409285892203e-05, "loss": 0.2365768551826477, "step": 1418 }, { "epoch": 0.6180313588850174, "grad_norm": 1.3085287809371948, "learning_rate": 2.5516052816765793e-05, "loss": 0.10925300419330597, "step": 1419 }, { "epoch": 0.6184668989547039, "grad_norm": 2.2321019172668457, "learning_rate": 2.547802014733406e-05, "loss": 0.2667495906352997, "step": 1420 }, { "epoch": 0.6189024390243902, "grad_norm": 1.5501893758773804, "learning_rate": 2.5439994913161986e-05, "loss": 0.18000830709934235, "step": 1421 }, { "epoch": 0.6193379790940766, "grad_norm": 1.5327757596969604, "learning_rate": 2.540197717677252e-05, "loss": 0.2532626986503601, "step": 1422 }, { "epoch": 0.6197735191637631, "grad_norm": 1.8870168924331665, "learning_rate": 2.5363967000676284e-05, "loss": 0.19920237362384796, "step": 1423 }, { "epoch": 0.6202090592334495, "grad_norm": 1.4490524530410767, "learning_rate": 2.532596444737145e-05, "loss": 0.14487847685813904, "step": 1424 }, { "epoch": 0.6206445993031359, "grad_norm": 1.9183648824691772, "learning_rate": 2.528796957934368e-05, "loss": 0.26750341057777405, "step": 1425 }, { "epoch": 0.6210801393728222, "grad_norm": 1.8421863317489624, "learning_rate": 2.5249982459065977e-05, "loss": 0.21623659133911133, "step": 1426 }, { "epoch": 0.6215156794425087, "grad_norm": 1.5806342363357544, "learning_rate": 2.521200314899863e-05, "loss": 0.17194150388240814, "step": 1427 }, { "epoch": 0.6219512195121951, "grad_norm": 1.8999648094177246, "learning_rate": 2.5174031711589053e-05, "loss": 0.2705439627170563, "step": 1428 }, { "epoch": 0.6223867595818815, "grad_norm": 2.4327075481414795, "learning_rate": 2.513606820927175e-05, "loss": 0.2698914110660553, "step": 1429 }, { "epoch": 0.622822299651568, "grad_norm": 2.175290107727051, "learning_rate": 2.5098112704468143e-05, "loss": 0.326336145401001, "step": 1430 }, { "epoch": 0.6232578397212544, "grad_norm": 1.9365315437316895, "learning_rate": 2.5060165259586534e-05, "loss": 0.2496911734342575, "step": 1431 }, { "epoch": 0.6236933797909407, "grad_norm": 1.4874533414840698, "learning_rate": 2.5022225937021976e-05, "loss": 0.1331433802843094, "step": 1432 }, { "epoch": 0.6241289198606271, "grad_norm": 2.000213384628296, "learning_rate": 2.4984294799156122e-05, "loss": 0.254539430141449, "step": 1433 }, { "epoch": 0.6245644599303136, "grad_norm": 1.0575778484344482, "learning_rate": 2.4946371908357228e-05, "loss": 0.09509436786174774, "step": 1434 }, { "epoch": 0.625, "grad_norm": 1.616779088973999, "learning_rate": 2.4908457326979935e-05, "loss": 0.18206360936164856, "step": 1435 }, { "epoch": 0.6254355400696864, "grad_norm": 1.5353922843933105, "learning_rate": 2.4870551117365256e-05, "loss": 0.18819403648376465, "step": 1436 }, { "epoch": 0.6258710801393729, "grad_norm": 1.2795904874801636, "learning_rate": 2.4832653341840436e-05, "loss": 0.1303432732820511, "step": 1437 }, { "epoch": 0.6263066202090593, "grad_norm": 1.371732473373413, "learning_rate": 2.479476406271883e-05, "loss": 0.16917970776557922, "step": 1438 }, { "epoch": 0.6267421602787456, "grad_norm": 1.4065773487091064, "learning_rate": 2.4756883342299848e-05, "loss": 0.11007710546255112, "step": 1439 }, { "epoch": 0.627177700348432, "grad_norm": 1.3483725786209106, "learning_rate": 2.471901124286881e-05, "loss": 0.14089597761631012, "step": 1440 }, { "epoch": 0.6276132404181185, "grad_norm": 1.765088677406311, "learning_rate": 2.4681147826696867e-05, "loss": 0.23051908612251282, "step": 1441 }, { "epoch": 0.6280487804878049, "grad_norm": 1.8232687711715698, "learning_rate": 2.4643293156040903e-05, "loss": 0.20895642042160034, "step": 1442 }, { "epoch": 0.6284843205574913, "grad_norm": 1.6689848899841309, "learning_rate": 2.46054472931434e-05, "loss": 0.15144582092761993, "step": 1443 }, { "epoch": 0.6289198606271778, "grad_norm": 2.043285846710205, "learning_rate": 2.4567610300232382e-05, "loss": 0.34985116124153137, "step": 1444 }, { "epoch": 0.6293554006968641, "grad_norm": 1.324885368347168, "learning_rate": 2.4529782239521267e-05, "loss": 0.12777724862098694, "step": 1445 }, { "epoch": 0.6297909407665505, "grad_norm": 1.8765711784362793, "learning_rate": 2.4491963173208803e-05, "loss": 0.2092246264219284, "step": 1446 }, { "epoch": 0.6302264808362369, "grad_norm": 11.779485702514648, "learning_rate": 2.445415316347894e-05, "loss": 0.4553186297416687, "step": 1447 }, { "epoch": 0.6306620209059234, "grad_norm": 1.4985606670379639, "learning_rate": 2.4416352272500732e-05, "loss": 0.1694854348897934, "step": 1448 }, { "epoch": 0.6310975609756098, "grad_norm": 1.8758090734481812, "learning_rate": 2.4378560562428255e-05, "loss": 0.24994255602359772, "step": 1449 }, { "epoch": 0.6315331010452961, "grad_norm": 1.7860504388809204, "learning_rate": 2.4340778095400493e-05, "loss": 0.2564220130443573, "step": 1450 }, { "epoch": 0.6319686411149826, "grad_norm": 2.191840410232544, "learning_rate": 2.4303004933541193e-05, "loss": 0.19239574670791626, "step": 1451 }, { "epoch": 0.632404181184669, "grad_norm": 2.4889702796936035, "learning_rate": 2.4265241138958836e-05, "loss": 0.643744945526123, "step": 1452 }, { "epoch": 0.6328397212543554, "grad_norm": 1.4116836786270142, "learning_rate": 2.4227486773746504e-05, "loss": 0.12972885370254517, "step": 1453 }, { "epoch": 0.6332752613240418, "grad_norm": 1.805114507675171, "learning_rate": 2.4189741899981755e-05, "loss": 0.20351508259773254, "step": 1454 }, { "epoch": 0.6337108013937283, "grad_norm": 2.1590287685394287, "learning_rate": 2.415200657972655e-05, "loss": 0.2742109000682831, "step": 1455 }, { "epoch": 0.6341463414634146, "grad_norm": 1.4852075576782227, "learning_rate": 2.411428087502715e-05, "loss": 0.14273783564567566, "step": 1456 }, { "epoch": 0.634581881533101, "grad_norm": 1.8010764122009277, "learning_rate": 2.4076564847913988e-05, "loss": 0.17351339757442474, "step": 1457 }, { "epoch": 0.6350174216027874, "grad_norm": 2.049821615219116, "learning_rate": 2.403885856040161e-05, "loss": 0.28086698055267334, "step": 1458 } ], "logging_steps": 1, "max_steps": 2526, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 6.628656222461829e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }